In [1]:
%run ADL_sea.ipynb
Number of input:  3
Number of output:  2
Number of batch:  200
All labeled
100% (200 of 200) |######################| Elapsed Time: 0:02:14 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.47537688442212 (+/-) 6.88610477180749
Testing Loss:  0.2420973918077784 (+/-) 0.174566812425013
Precision:  0.9252151888619986
Recall:  0.9247537688442211
F1 score:  0.9240104512920709
Testing Time:  0.0026751295406015675 (+/-) 0.003450418901497672
Training Time:  0.6739132631963222 (+/-) 0.04991744609300713


=== Average network evolution ===
Total hidden node:  11.557788944723619 (+/-) 4.318410643757607
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=19, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=19, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 19
No. of parameters : 116
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:02:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.39899497487438 (+/-) 7.31767317516075
Testing Loss:  0.24268003636456315 (+/-) 0.17876836341987254
Precision:  0.9245291800410059
Recall:  0.9239899497487437
F1 score:  0.9232049062219255
Testing Time:  0.002700068842825578 (+/-) 0.003790747152800348
Training Time:  0.6994425327933613 (+/-) 0.07097746397496776


=== Average network evolution ===
Total hidden node:  10.537688442211055 (+/-) 4.302311717435989
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=18, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=18, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 18
No. of parameters : 110
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:02:22 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.21608040201005 (+/-) 7.6784985127706396
Testing Loss:  0.2438871257344083 (+/-) 0.18202602448016147
Precision:  0.922751258284536
Recall:  0.9221608040201005
F1 score:  0.9213232590133877
Testing Time:  0.002500949792526475 (+/-) 0.0024791113219701853
Training Time:  0.7138597078658827 (+/-) 0.06081365743068822


=== Average network evolution ===
Total hidden node:  11.773869346733669 (+/-) 4.966634463344113
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 20
No. of parameters : 122
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:02:23 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.45427135678392 (+/-) 7.024828140155979
Testing Loss:  0.2457714871639133 (+/-) 0.17994961621511688
Precision:  0.924898421882622
Recall:  0.9245427135678392
F1 score:  0.9238355155454488
Testing Time:  0.0027041926455857166 (+/-) 0.003274716189284338
Training Time:  0.715763185491514 (+/-) 0.03692923894375927


=== Average network evolution ===
Total hidden node:  11.608040201005025 (+/-) 4.432308934499736
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=19, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=19, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 19
No. of parameters : 116
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:02:15 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.37688442211055 (+/-) 7.188241958502679
Testing Loss:  0.2415224832094195 (+/-) 0.17916739408981872
Precision:  0.9240753575339399
Recall:  0.9237688442211055
F1 score:  0.9230677109809373
Testing Time:  0.0024214629551873135 (+/-) 0.00301272470123567
Training Time:  0.674902778175009 (+/-) 0.04646547160194004


=== Average network evolution ===
Total hidden node:  11.85427135678392 (+/-) 5.354176442143243
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 20
No. of parameters : 122
Voting weight:  [1.0]
Mean Accuracy:  92.52585858585859
Std Accuracy:  6.96149569005313
Hidden Node mean 11.495959595959595
Hidden Node std:  4.710774651429352
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (200 of 200) |######################| Elapsed Time: 0:01:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.78391959798995 (+/-) 9.749533822823517
Testing Loss:  0.2673834305275325 (+/-) 0.18655504090906838
Precision:  0.9103782945359641
Recall:  0.9078391959798995
F1 score:  0.9060898386562237
Testing Time:  0.0023695643822751454 (+/-) 0.0035019492575508343
Training Time:  0.32802253152856875 (+/-) 0.019634724509234057


=== Average network evolution ===
Total hidden node:  6.562814070351759 (+/-) 3.979195156191552
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=14, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=14, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 14
No. of parameters : 86
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:01:07 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.52864321608038 (+/-) 9.134326096352938
Testing Loss:  0.27593131022686934 (+/-) 0.1839924027924849
Precision:  0.9072036494542475
Recall:  0.9052864321608041
F1 score:  0.9036280131122092
Testing Time:  0.002502805623576869 (+/-) 0.0037284154085801035
Training Time:  0.33625364303588867 (+/-) 0.025852237269212326


=== Average network evolution ===
Total hidden node:  6.673366834170854 (+/-) 3.1075922947609795
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 13
No. of parameters : 80
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:01:10 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.48341708542713 (+/-) 10.193745071110198
Testing Loss:  0.27469674441682634 (+/-) 0.1932502877801274
Precision:  0.9067718159107777
Recall:  0.9048341708542713
F1 score:  0.9031563547332235
Testing Time:  0.00270002930607628 (+/-) 0.0038024585217603067
Training Time:  0.35018755802557094 (+/-) 0.02417822682621283


=== Average network evolution ===
Total hidden node:  9.256281407035177 (+/-) 4.094321136531829
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=17, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=17, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 17
No. of parameters : 104
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:01:07 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.20904522613064 (+/-) 8.16900125477204
Testing Loss:  0.2695008166246678 (+/-) 0.17643954343959203
Precision:  0.9135044486743105
Recall:  0.9120904522613066
F1 score:  0.9107668854219414
Testing Time:  0.00265337234765441 (+/-) 0.003954456923554642
Training Time:  0.3335821053490567 (+/-) 0.019540475833703504


=== Average network evolution ===
Total hidden node:  8.14572864321608 (+/-) 3.4805806346795354
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=15, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 15
No. of parameters : 92
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:01:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.33467336683417 (+/-) 7.45389539446337
Testing Loss:  0.2715872459151038 (+/-) 0.16798782376932672
Precision:  0.9140176915452691
Recall:  0.9133467336683417
F1 score:  0.9122965392272976
Testing Time:  0.002801953847683854 (+/-) 0.003934641437488994
Training Time:  0.3316702207728247 (+/-) 0.025133046721970302


=== Average network evolution ===
Total hidden node:  14.698492462311558 (+/-) 3.7105780799127666
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=21, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=21, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 21
No. of parameters : 128
Voting weight:  [1.0]
N/A% (0 of 200) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--
Mean Accuracy:  91.02020202020202
Std Accuracy:  8.719952504249067
Hidden Node mean 9.082828282828283
Hidden Node std:  4.753011600400689
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (200 of 200) |######################| Elapsed Time: 0:00:35 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.96381909547738 (+/-) 10.76065312916779
Testing Loss:  0.3043554661861017 (+/-) 0.18843773360041083
Precision:  0.8946260321476117
Recall:  0.8896381909547739
F1 score:  0.8865929888749416
Testing Time:  0.0022217412689822403 (+/-) 0.0037598725181260074
Training Time:  0.17327104141963787 (+/-) 0.01738355145084289


=== Average network evolution ===
Total hidden node:  4.442211055276382 (+/-) 2.718894827146466
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=10, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 10
No. of parameters : 62
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:00:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.50351758793968 (+/-) 11.914803835592318
Testing Loss:  0.32693379829127583 (+/-) 0.2012860146787662
Precision:  0.8808548967987914
Recall:  0.8750351758793969
F1 score:  0.8710439299665473
Testing Time:  0.0021707316738876267 (+/-) 0.0031799967854169208
Training Time:  0.18048469744735027 (+/-) 0.017121671889080575


=== Average network evolution ===
Total hidden node:  5.42713567839196 (+/-) 2.29998193933993
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=9, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 9
No. of parameters : 56
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:00:35 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.9286432160804 (+/-) 11.231413844797423
Testing Loss:  0.30603738147859 (+/-) 0.1938833172955363
Precision:  0.8939750750368572
Recall:  0.889286432160804
F1 score:  0.8863000789115422
Testing Time:  0.0022210595595776733 (+/-) 0.00275415620605113
Training Time:  0.1719920982667549 (+/-) 0.013481649668472503


=== Average network evolution ===
Total hidden node:  7.21608040201005 (+/-) 3.0602891303559394
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 13
No. of parameters : 80
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:00:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.22110552763817 (+/-) 9.428735975431254
Testing Loss:  0.3055427845324104 (+/-) 0.17419639722515848
Precision:  0.8960722811974832
Recall:  0.8922110552763819
F1 score:  0.8895626203933883
Testing Time:  0.0019633829893179276 (+/-) 0.0028245622885234144
Training Time:  0.1628216151616082 (+/-) 0.010683908191211037


=== Average network evolution ===
Total hidden node:  6.814070351758794 (+/-) 1.9723217996774234
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=11, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 11
No. of parameters : 68
Voting weight:  [1.0]
100% (200 of 200) |######################| Elapsed Time: 0:00:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.27939698492462 (+/-) 11.447671095280452
Testing Loss:  0.3218272822211735 (+/-) 0.19539244023833321
Precision:  0.88193266430969
Recall:  0.8727939698492462
F1 score:  0.8678313319880798
Testing Time:  0.001976243215589667 (+/-) 0.0029755320140556914
Training Time:  0.16283929048471116 (+/-) 0.010076730269205683


=== Average network evolution ===
Total hidden node:  4.567839195979899 (+/-) 2.6246169099300585
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=10, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 10
No. of parameters : 62
Voting weight:  [1.0]
Mean Accuracy:  88.5
Std Accuracy:  10.915561128383404
Hidden Node mean 5.702020202020202
Hidden Node std:  2.806395286598519
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
 94% (188 of 200) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  63.03636363636364 (+/-) 7.620592179135286
Testing Loss:  0.6486203345385465 (+/-) 0.036306491302862384
Precision:  0.3973583140495867
Recall:  0.6303636363636363
F1 score:  0.4874474690025041
Testing Time:  0.0015305690091065687 (+/-) 0.0033436282702815363
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 5
No. of parameters : 32
Voting weight:  [1.0]
 91% (183 of 200) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  72.82222222222222 (+/-) 5.881584950196236
Testing Loss:  0.5691407699175556 (+/-) 0.03156485015610682
Precision:  0.7592566887363517
Recall:  0.7282222222222222
F1 score:  0.6884780357252303
Testing Time:  0.0013918190291433623 (+/-) 0.002365142297307859
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  6.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 6
No. of parameters : 38
Voting weight:  [1.0]
 95% (190 of 200) |####################  | Elapsed Time: 0:00:00 ETA:   0:00:00

=== Performance result ===
Accuracy:  63.66464646464646 (+/-) 7.618151014190566
Testing Loss:  0.5589947190248605 (+/-) 0.06280817529548549
Precision:  0.7542900127698696
Recall:  0.6366464646464647
F1 score:  0.5021764906454884
Testing Time:  0.0013549857669406468 (+/-) 0.00272378270729878
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 4
No. of parameters : 26
Voting weight:  [1.0]
 99% (198 of 200) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  63.03636363636364 (+/-) 7.620592179135286
Testing Loss:  0.6580547112407107 (+/-) 0.03950826087293183
Precision:  0.3973583140495867
Recall:  0.6303636363636363
F1 score:  0.4874474690025041
Testing Time:  0.0015402899848090278 (+/-) 0.0024318230902579774
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  3.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 3
No. of parameters : 20
Voting weight:  [1.0]
 90% (180 of 200) |###################   | Elapsed Time: 0:00:00 ETA:   0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  63.03636363636364 (+/-) 7.620592179135286
Testing Loss:  0.6202581007071216 (+/-) 0.062000340626009634
Precision:  0.3973583140495867
Recall:  0.6303636363636363
F1 score:  0.4874474690025041
Testing Time:  0.0014716278422962535 (+/-) 0.0026561803544853076
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 5
No. of parameters : 32
Voting weight:  [1.0]
Mean Accuracy:  65.11695431472081
Std Accuracy:  8.279599224155337
Hidden Node mean 4.6
Hidden Node std:  1.019803902718557
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [2]:
%run ADL_hyperplane.ipynb
Number of input:  4
Number of output:  2
Number of batch:  240
All labeled
100% (240 of 240) |######################| Elapsed Time: 0:02:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.61924686192468 (+/-) 5.382332583117983
Testing Loss:  0.2994545329689481 (+/-) 0.07708712246012778
Precision:  0.9162176533706246
Recall:  0.9161924686192469
F1 score:  0.9161907058544578
Testing Time:  0.0024280777536176737 (+/-) 0.0032747757773265093
Training Time:  0.6493809592274942 (+/-) 0.012592105367956111


=== Average network evolution ===
Total hidden node:  2.430962343096234 (+/-) 0.4952108661259746
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 3
No. of parameters : 23
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:02:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.12217573221756 (+/-) 5.572148488763887
Testing Loss:  0.28600116791086716 (+/-) 0.07643516977094293
Precision:  0.921232767842197
Recall:  0.9212217573221757
F1 score:  0.9212215337456449
Testing Time:  0.0023531005971102535 (+/-) 0.0034522620791369602
Training Time:  0.6532286041451298 (+/-) 0.020995350565822118


=== Average network evolution ===
Total hidden node:  2.589958158995816 (+/-) 0.4918409596913249
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 3
No. of parameters : 23
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:02:41 ETA:  00:00:00

=== Performance result ===
Accuracy:  91.64100418410041 (+/-) 6.137107846165298
Testing Loss:  0.30302848732371707 (+/-) 0.07915096495004463
Precision:  0.9164348373973619
Recall:  0.9164100418410042
F1 score:  0.9164092702057459
Testing Time:  0.002542788014751099 (+/-) 0.0034965857839544456
Training Time:  0.6693316304035266 (+/-) 0.03165348960391427


=== Average network evolution ===
Total hidden node:  4.644351464435147 (+/-) 0.4787093635134252
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:02:40 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.10794979079496 (+/-) 3.55912105140678
Testing Loss:  0.2987334580476314 (+/-) 0.054023127573923094
Precision:  0.9210825329045311
Recall:  0.9210794979079497
F1 score:  0.9210795055180077
Testing Time:  0.0025220346251292208 (+/-) 0.0032398871077608145
Training Time:  0.6686275354489123 (+/-) 0.04634983655650105


=== Average network evolution ===
Total hidden node:  5.171548117154812 (+/-) 0.6844553990520008
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:02:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  92.0970711297071 (+/-) 5.428018104525603
Testing Loss:  0.2901938641794556 (+/-) 0.0716536076580636
Precision:  0.9209809247027151
Recall:  0.9209707112970711
F1 score:  0.920969935793622
Testing Time:  0.002857000757959597 (+/-) 0.0048643768264168274
Training Time:  0.7466373882533117 (+/-) 0.07452561989378949


=== Average network evolution ===
Total hidden node:  2.0460251046025104 (+/-) 0.2928272503250659
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=2, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 2
No. of parameters : 16
Voting weight:  [1.0]
Mean Accuracy:  92.06773109243699
Std Accuracy:  4.763243446368177
Hidden Node mean 3.3747899159663866
Hidden Node std:  1.3716345207035683
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (240 of 240) |######################| Elapsed Time: 0:01:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.60502092050208 (+/-) 8.689548855331084
Testing Loss:  0.3280997356735014 (+/-) 0.10045905049061794
Precision:  0.8960511485376287
Recall:  0.8960502092050209
F1 score:  0.8960502569570513
Testing Time:  0.00269587369144711 (+/-) 0.004033753233156096
Training Time:  0.36741442061867174 (+/-) 0.044003626425751625


=== Average network evolution ===
Total hidden node:  5.372384937238493 (+/-) 0.7649698235243142
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 6
No. of parameters : 44
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:01:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.66861924686192 (+/-) 8.908665952647674
Testing Loss:  0.32853061291213814 (+/-) 0.10377740946932923
Precision:  0.8966885309187882
Recall:  0.8966861924686192
F1 score:  0.8966858335654025
Testing Time:  0.002634387634788098 (+/-) 0.0035627971433064226
Training Time:  0.3630629503577324 (+/-) 0.03916672000436552


=== Average network evolution ===
Total hidden node:  3.1673640167364017 (+/-) 0.8061101374404644
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 4
No. of parameters : 30
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:01:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  90.35146443514644 (+/-) 6.294686936575027
Testing Loss:  0.3367532365117612 (+/-) 0.08452332883426067
Precision:  0.9035486193480714
Recall:  0.9035146443514644
F1 score:  0.9035119297376629
Testing Time:  0.002540052685278729 (+/-) 0.003186597107329377
Training Time:  0.3291768119923739 (+/-) 0.013842045676363228


=== Average network evolution ===
Total hidden node:  4.640167364016737 (+/-) 1.3398532257489828
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 6
No. of parameters : 44
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:01:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.02594142259413 (+/-) 9.334427921185933
Testing Loss:  0.3605628171974645 (+/-) 0.12025257311362389
Precision:  0.8803014432454552
Recall:  0.8802594142259415
F1 score:  0.880255098053841
Testing Time:  0.0024827324695666964 (+/-) 0.003224533863789907
Training Time:  0.32883843816972674 (+/-) 0.013912471906591506


=== Average network evolution ===
Total hidden node:  2.271966527196653 (+/-) 0.4449727354358299
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=2, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 2
No. of parameters : 16
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:01:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.58995815899581 (+/-) 9.388762066232408
Testing Loss:  0.331794539193728 (+/-) 0.10771929103267788
Precision:  0.8964049703202955
Recall:  0.8958995815899582
F1 score:  0.8958635268390198
Testing Time:  0.0028289102610185054 (+/-) 0.0049145376587710135
Training Time:  0.34681823662634176 (+/-) 0.02145336973330533


=== Average network evolution ===
Total hidden node:  4.2301255230125525 (+/-) 0.6607435149981983
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
N/A% (0 of 240) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--
Mean Accuracy:  89.62268907563025
Std Accuracy:  8.213634258162184
Hidden Node mean 3.938655462184874
Hidden Node std:  1.3916080562191462
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (240 of 240) |######################| Elapsed Time: 0:00:41 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.33974895397492 (+/-) 9.798354482493014
Testing Loss:  0.35377315341428733 (+/-) 0.11316917112280157
Precision:  0.8836314964942191
Recall:  0.883397489539749
F1 score:  0.8833774382750127
Testing Time:  0.0021852279806735624 (+/-) 0.0037070249033979204
Training Time:  0.1695471418452562 (+/-) 0.013540274851084373


=== Average network evolution ===
Total hidden node:  4.958158995815899 (+/-) 0.22013299477767206
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:00:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.55732217573224 (+/-) 6.895491428047614
Testing Loss:  0.3437017963022368 (+/-) 0.10074823058498715
Precision:  0.8956303902354521
Recall:  0.8955732217573221
F1 score:  0.8955684716278671
Testing Time:  0.0025747121627360705 (+/-) 0.0040421790607353585
Training Time:  0.18525898207181668 (+/-) 0.02024829630558933


=== Average network evolution ===
Total hidden node:  3.0418410041841004 (+/-) 0.8068264966154947
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 4
No. of parameters : 30
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:00:48 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.6794979079498 (+/-) 7.041363011047143
Testing Loss:  0.33780838729946183 (+/-) 0.0870487334977934
Precision:  0.8968148051251472
Recall:  0.8967949790794979
F1 score:  0.896793117075348
Testing Time:  0.0026705574291021753 (+/-) 0.005642939509886746
Training Time:  0.19961824177698112 (+/-) 0.027489794627419302


=== Average network evolution ===
Total hidden node:  3.6317991631799162 (+/-) 1.286554749260399
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=2, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 2
No. of parameters : 16
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:00:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.3723849372385 (+/-) 6.44937081053829
Testing Loss:  0.34281873678063746 (+/-) 0.0943098900835162
Precision:  0.893882473861106
Recall:  0.8937238493723849
F1 score:  0.8937114928364053
Testing Time:  0.0023850097815860762 (+/-) 0.0037719594898348893
Training Time:  0.17591660790862398 (+/-) 0.015445830944554607


=== Average network evolution ===
Total hidden node:  4.552301255230126 (+/-) 0.5298465646285098
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
100% (240 of 240) |######################| Elapsed Time: 0:00:47 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.84351464435146 (+/-) 10.712185109631335
Testing Loss:  0.35770354404359683 (+/-) 0.11132133416153382
Precision:  0.8784824356103664
Recall:  0.8784351464435146
F1 score:  0.8784302591488962
Testing Time:  0.0026878751970235274 (+/-) 0.004220639753273804
Training Time:  0.19412217080343716 (+/-) 0.021815606326937558


=== Average network evolution ===
Total hidden node:  5.083682008368201 (+/-) 0.6916306601149412
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 6
No. of parameters : 44
Voting weight:  [1.0]
Mean Accuracy:  89.12420168067229
Std Accuracy:  8.00382277318376
Hidden Node mean 4.249579831932773
Hidden Node std:  1.1170469735449151
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
 97% (234 of 240) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  81.68319327731092 (+/-) 2.2196910727491335
Testing Loss:  0.6541204913323667 (+/-) 0.0021516251926301322
Precision:  0.8296084739783834
Recall:  0.8168319327731093
F1 score:  0.8150031817190354
Testing Time:  0.002143259809798553 (+/-) 0.003772147479357388
Training Time:  4.232430658420595e-06 (+/-) 6.515744177733074e-05


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 4
No. of parameters : 30
Voting weight:  [1.0]
 95% (228 of 240) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  79.60420168067228 (+/-) 2.362767745994045
Testing Loss:  0.630295464972488 (+/-) 0.004018039388453913
Precision:  0.8249541986146729
Recall:  0.7960420168067227
F1 score:  0.7913393196457598
Testing Time:  0.0022465902216294233 (+/-) 0.004656646648446849
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  3.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 3
No. of parameters : 23
Voting weight:  [1.0]
 96% (231 of 240) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  60.17563025210084 (+/-) 2.2385269160862897
Testing Loss:  0.6342612692788869 (+/-) 0.008613439970348672
Precision:  0.7553771519023468
Recall:  0.6017563025210084
F1 score:  0.5317131947386157
Testing Time:  0.0020658639298767605 (+/-) 0.004100768714369769
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 4
No. of parameters : 30
Voting weight:  [1.0]
 93% (225 of 240) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  59.59159663865546 (+/-) 2.196160891380465
Testing Loss:  0.6770254553866988 (+/-) 0.0028720740568141485
Precision:  0.7264134360739493
Recall:  0.5959159663865546
F1 score:  0.5283703438037782
Testing Time:  0.00219577200272504 (+/-) 0.0037161395336315103
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
 98% (237 of 240) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  52.94705882352942 (+/-) 2.355980180303979
Testing Loss:  0.6685473347912315 (+/-) 0.007270724783126856
Precision:  0.7335600646016379
Recall:  0.5294705882352941
F1 score:  0.39871695076751057
Testing Time:  0.0021492733674890853 (+/-) 0.004349772483060783
Training Time:  4.189355032784599e-06 (+/-) 6.449430094977448e-05


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=4, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 4
No. of nodes : 5
No. of parameters : 37
Voting weight:  [1.0]
Mean Accuracy:  66.79476793248945
Std Accuracy:  11.833397904186391
Hidden Node mean 4.2
Hidden Node std:  0.7483314773547883
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [3]:
%run ADL_weather.ipynb
Number of input:  8
Number of output:  2
Number of batch:  36
All labeled
100% (36 of 36) |########################| Elapsed Time: 0:00:26 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.29142857142858 (+/-) 4.376650475849666
Testing Loss:  0.5603172157491957 (+/-) 0.04864075346586718
Precision:  0.6753161967968139
Recall:  0.7029142857142857
F1 score:  0.6660907946580805
Testing Time:  0.0020109380994524275 (+/-) 0.0010536084021678846
Training Time:  0.7386781283787318 (+/-) 0.24422472584832222


=== Average network evolution ===
Total hidden node:  6.428571428571429 (+/-) 0.4948716593053935
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:26 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.41142857142857 (+/-) 4.45830021603823
Testing Loss:  0.5390180970941271 (+/-) 0.05275780424419407
Precision:  0.6921029670566003
Recall:  0.7141142857142857
F1 score:  0.6744157587491696
Testing Time:  0.003435380118233817 (+/-) 0.007631229583872514
Training Time:  0.7403532028198242 (+/-) 0.17609482484291333


=== Average network evolution ===
Total hidden node:  6.6571428571428575 (+/-) 0.5827450872677469
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:26 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.17714285714285 (+/-) 4.148327422969801
Testing Loss:  0.5535387413842338 (+/-) 0.058574801819985325
Precision:  0.6882273305205227
Recall:  0.7117714285714286
F1 score:  0.6749798701459082
Testing Time:  0.0020357472555977956 (+/-) 0.00046893483673929846
Training Time:  0.7408656324659075 (+/-) 0.0535308196386972


=== Average network evolution ===
Total hidden node:  6.771428571428571 (+/-) 0.6797358430497326
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 101
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.21142857142856 (+/-) 3.94155672136722
Testing Loss:  0.5432083913258143 (+/-) 0.04873687066182523
Precision:  0.6895148364901516
Recall:  0.7121142857142857
F1 score:  0.6692107662229916
Testing Time:  0.0021268231528145925 (+/-) 0.00048225709923842394
Training Time:  0.7328625406537738 (+/-) 0.18463343284896594


=== Average network evolution ===
Total hidden node:  6.3428571428571425 (+/-) 0.4746642207381757
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  71.48571428571428 (+/-) 4.30900338872942
Testing Loss:  0.5373030432632991 (+/-) 0.04702161515288952
Precision:  0.6951253218095428
Recall:  0.7148571428571429
F1 score:  0.6948906805456576
Testing Time:  0.0019490242004394532 (+/-) 0.0004504565675305782
Training Time:  0.6975211415972028 (+/-) 0.16406499271991057


=== Average network evolution ===
Total hidden node:  7.0285714285714285 (+/-) 0.5062870041905528
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 101
Voting weight:  [1.0]
Mean Accuracy:  71.33647058823529
Std Accuracy:  4.1326489741148595
Hidden Node mean 6.6647058823529415
Hidden Node std:  0.593534950128652
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (36 of 36) |########################| Elapsed Time: 0:00:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.79999999999998 (+/-) 4.225095096140271
Testing Loss:  0.568497302702495 (+/-) 0.04643767822172233
Precision:  0.6703645846943086
Recall:  0.698
F1 score:  0.6262666403970503
Testing Time:  0.0018880162920270648 (+/-) 0.0004995125572197143
Training Time:  0.3426097461155483 (+/-) 0.021421758937124717


=== Average network evolution ===
Total hidden node:  5.914285714285715 (+/-) 0.49979587670102565
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.03999999999999 (+/-) 4.432039195288262
Testing Loss:  0.5747504830360413 (+/-) 0.04755894931252556
Precision:  0.6774331658051788
Recall:  0.7004
F1 score:  0.6276555197754108
Testing Time:  0.0018604482923235213 (+/-) 0.0004626668745170628
Training Time:  0.34218998636518205 (+/-) 0.01608545623308812


=== Average network evolution ===
Total hidden node:  6.8 (+/-) 0.39999999999999997
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.13714285714283 (+/-) 4.220973869637582
Testing Loss:  0.5655117792742593 (+/-) 0.03979251845321257
Precision:  0.6766805128249144
Recall:  0.7013714285714285
F1 score:  0.6344410167816626
Testing Time:  0.001930373055594308 (+/-) 0.0005812613030092886
Training Time:  0.3663158416748047 (+/-) 0.04233670725271423


=== Average network evolution ===
Total hidden node:  5.885714285714286 (+/-) 0.4642307659791977
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:13 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.11428571428571 (+/-) 4.490825113949732
Testing Loss:  0.556182290826525 (+/-) 0.046483354730274304
Precision:  0.6728749397121206
Recall:  0.7011428571428572
F1 score:  0.6437564109718324
Testing Time:  0.0030959129333496095 (+/-) 0.007528412511258433
Training Time:  0.37491981642586847 (+/-) 0.036138210556301766


=== Average network evolution ===
Total hidden node:  6.2 (+/-) 0.39999999999999997
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:12 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.18857142857142 (+/-) 4.662542006157549
Testing Loss:  0.5824429069246565 (+/-) 0.041398074528288795
Precision:  0.6843182318966381
Recall:  0.6918857142857143
F1 score:  0.5850625545872097
Testing Time:  0.0018378325871058873 (+/-) 0.0004865534644811643
Training Time:  0.3477430820465088 (+/-) 0.020621625905158585


=== Average network evolution ===
Total hidden node:  5.114285714285714 (+/-) 0.318157963590287
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
Mean Accuracy:  70.03999999999999
Std Accuracy:  4.3542865965282855
Hidden Node mean 5.9941176470588236
Hidden Node std:  0.6729833388684029
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (36 of 36) |########################| Elapsed Time: 0:00:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.27428571428571 (+/-) 5.377856336451375
Testing Loss:  0.6056071230343409 (+/-) 0.04500709694597638
Precision:  0.6272728651657223
Recall:  0.6827428571428571
F1 score:  0.595136312006994
Testing Time:  0.0015383924756731306 (+/-) 0.0004981429603623633
Training Time:  0.17295222282409667 (+/-) 0.01187024822655671


=== Average network evolution ===
Total hidden node:  7.3428571428571425 (+/-) 0.4746642207381757
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  70.76571428571428 (+/-) 3.923987975599958
Testing Loss:  0.5549135335854122 (+/-) 0.04424477072355443
Precision:  0.689669199362978
Recall:  0.7076571428571429
F1 score:  0.6444427087463735
Testing Time:  0.0015115397317068918 (+/-) 0.0004987801339801137
Training Time:  0.1816798346383231 (+/-) 0.019381657726824937


=== Average network evolution ===
Total hidden node:  8.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.59428571428572 (+/-) 5.094643846076715
Testing Loss:  0.592691513470241 (+/-) 0.04850196512822754
Precision:  0.6375194670468896
Recall:  0.6859428571428572
F1 score:  0.5912795001106645
Testing Time:  0.001851585933140346 (+/-) 0.00048575638179954375
Training Time:  0.19108799525669642 (+/-) 0.015204977644463286


=== Average network evolution ===
Total hidden node:  6.742857142857143 (+/-) 0.43705881545081016
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 6
No. of parameters : 68
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  69.16000000000001 (+/-) 5.022645859362516
Testing Loss:  0.5884550264903478 (+/-) 0.03993871637412888
Precision:  0.6786299149186737
Recall:  0.6916
F1 score:  0.5860484288258995
Testing Time:  0.003051280975341797 (+/-) 0.008394083795294457
Training Time:  0.18359429495675222 (+/-) 0.018547829356493586


=== Average network evolution ===
Total hidden node:  5.857142857142857 (+/-) 0.3499271061118826
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 6
No. of parameters : 68
Voting weight:  [1.0]
100% (36 of 36) |########################| Elapsed Time: 0:00:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  68.37142857142857 (+/-) 5.12788296214621
Testing Loss:  0.6110692228589739 (+/-) 0.0441945344667759
Precision:  0.6229808252718423
Recall:  0.6837142857142857
F1 score:  0.5745587746644596
Testing Time:  0.0017094407762799945 (+/-) 0.0006119627351107019
Training Time:  0.18425038201468333 (+/-) 0.025416198429328768


=== Average network evolution ===
Total hidden node:  5.171428571428572 (+/-) 0.37688302737922635
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
Mean Accuracy:  69.19294117647058
Std Accuracy:  5.005168816223159
Hidden Node mean 6.629411764705883
Hidden Node std:  1.0727999133012824
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
  5% (2 of 36) |#                        | Elapsed Time: 0:00:00 ETA:   0:00:11C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 5.16458528600996
Testing Loss:  0.6579263087581185 (+/-) 0.009342899854395447
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.0008799959631527171 (+/-) 0.0004023326871068336
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  7.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
 97% (35 of 36) |####################### | Elapsed Time: 0:00:00 ETA:   0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 5.16458528600996
Testing Loss:  0.6028559856555041 (+/-) 0.03574550459060763
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.001261318431181066 (+/-) 0.000555834964380562
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  7.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
  5% (2 of 36) |#                        | Elapsed Time: 0:00:00 ETA:   0:00:11C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 5.16458528600996
Testing Loss:  0.6260132140973035 (+/-) 0.036060178115815446
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.0011140248354743509 (+/-) 0.00046972028819113
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  9.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 101
Voting weight:  [1.0]
 19% (7 of 36) |####                     | Elapsed Time: 0:00:00 ETA:   0:00:10C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 5.16458528600996
Testing Loss:  0.6113338330212761 (+/-) 0.029883802257597958
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.0027571986703311697 (+/-) 0.009076499786360336
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
 88% (32 of 36) |#####################   | Elapsed Time: 0:00:00 ETA:   0:00:01C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  68.60000000000001 (+/-) 5.16458528600996
Testing Loss:  0.6157613940098706 (+/-) 0.04607704347878779
Precision:  0.470596
Recall:  0.686
F1 score:  0.5582396204033215
Testing Time:  0.0011732858770033892 (+/-) 0.0003826204326335119
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
Mean Accuracy:  68.43030303030304
Std Accuracy:  5.148020204834549
Hidden Node mean 6.6
Hidden Node std:  1.4966629547095767
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [4]:
%run ADL_rfid.ipynb
Number of input:  3
Number of output:  4
Number of batch:  560
All labeled
100% (560 of 560) |######################| Elapsed Time: 0:07:07 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.02754919499105 (+/-) 7.7213010367537
Testing Loss:  0.10583574941701694 (+/-) 0.19977435405127758
Precision:  0.9802631927667363
Recall:  0.9802754919499106
F1 score:  0.98024016923772
Testing Time:  0.004872995966875489 (+/-) 0.005325282590282859
Training Time:  0.7564038125688147 (+/-) 0.06931505400848331


=== Average network evolution ===
Total hidden node:  32.833631484794275 (+/-) 11.311931716368724
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=44, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=44, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 44
No. of parameters : 356
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:07:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.31377459749554 (+/-) 6.542701888855917
Testing Loss:  0.09517400123742084 (+/-) 0.18718034556961077
Precision:  0.9831476479309779
Recall:  0.9831377459749553
F1 score:  0.9831030644810734
Testing Time:  0.005186723681809864 (+/-) 0.005643882638682042
Training Time:  0.7721664031204469 (+/-) 0.06594642737183061


=== Average network evolution ===
Total hidden node:  36.840787119856884 (+/-) 10.642073154523906
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=47, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=47, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 47
No. of parameters : 380
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:06:28 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.26833631484794 (+/-) 6.980226294927336
Testing Loss:  0.10266793742009533 (+/-) 0.18976685920413258
Precision:  0.9827022056623266
Recall:  0.9826833631484795
F1 score:  0.9826588410628426
Testing Time:  0.0046912775056733216 (+/-) 0.0038253311855971253
Training Time:  0.6874949053489672 (+/-) 0.04431513562517215


=== Average network evolution ===
Total hidden node:  31.43649373881932 (+/-) 10.184829955884528
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=41, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=41, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 41
No. of parameters : 332
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:06:19 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.08908765652953 (+/-) 7.070430683076858
Testing Loss:  0.11407390756995713 (+/-) 0.20877548833869164
Precision:  0.9808662049106773
Recall:  0.9808908765652952
F1 score:  0.9808494875699509
Testing Time:  0.0046198086576512976 (+/-) 0.0037262644740469215
Training Time:  0.670405328593655 (+/-) 0.02927101698006069


=== Average network evolution ===
Total hidden node:  30.987477638640428 (+/-) 11.10986864432801
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=42, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=42, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 42
No. of parameters : 340
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:06:21 ETA:  00:00:00

=== Performance result ===
Accuracy:  98.19570661896243 (+/-) 6.984930072254507
Testing Loss:  0.09648956943300015 (+/-) 0.1924690357670467
Precision:  0.9820246842664342
Recall:  0.9819570661896243
F1 score:  0.9819110920128582
Testing Time:  0.004874389798568698 (+/-) 0.004377899296036244
Training Time:  0.6733644737967012 (+/-) 0.04463943449538615


=== Average network evolution ===
Total hidden node:  34.51520572450805 (+/-) 11.067658305986456
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=45, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=45, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 45
No. of parameters : 364
Voting weight:  [1.0]
Mean Accuracy:  98.29025089605734
Std Accuracy:  6.558571912272443
Hidden Node mean 33.37132616487455
Hidden Node std:  11.030867510138673
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (560 of 560) |######################| Elapsed Time: 0:03:07 ETA:  00:00:00

=== Performance result ===
Accuracy:  97.19141323792486 (+/-) 9.139088118310458
Testing Loss:  0.1602632498371953 (+/-) 0.22863448992052193
Precision:  0.9719292578200124
Recall:  0.9719141323792486
F1 score:  0.971916964760968
Testing Time:  0.004576175072112109 (+/-) 0.004125611984330837
Training Time:  0.3270158076755476 (+/-) 0.01677785599647808


=== Average network evolution ===
Total hidden node:  30.608228980322004 (+/-) 8.436991781202778
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=40, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=40, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 40
No. of parameters : 324
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:03:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  97.28443649373882 (+/-) 9.110863063168381
Testing Loss:  0.1588941642944576 (+/-) 0.2391616034399491
Precision:  0.9728152598324031
Recall:  0.9728443649373882
F1 score:  0.9727742203518411
Testing Time:  0.004511605008556932 (+/-) 0.003586433155762893
Training Time:  0.319773612167413 (+/-) 0.01299459331266135


=== Average network evolution ===
Total hidden node:  31.069767441860463 (+/-) 9.573954593838387
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=41, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=41, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 41
No. of parameters : 332
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:03:02 ETA:  00:00:00

=== Performance result ===
Accuracy:  96.84114490161001 (+/-) 10.784555781853948
Testing Loss:  0.18069382194489614 (+/-) 0.2635218865173473
Precision:  0.9683720646868362
Recall:  0.9684114490161002
F1 score:  0.9683720892766532
Testing Time:  0.0040993131763819935 (+/-) 0.0034184466562314168
Training Time:  0.31974434212836467 (+/-) 0.016316177057959277


=== Average network evolution ===
Total hidden node:  23.887298747763865 (+/-) 8.885668127381456
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=34, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=34, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 34
No. of parameters : 276
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:03:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  97.16064400715564 (+/-) 9.47928861488502
Testing Loss:  0.16395533588350034 (+/-) 0.24623985928762596
Precision:  0.971592994756987
Recall:  0.9716064400715564
F1 score:  0.9715195558415151
Testing Time:  0.004318036418907971 (+/-) 0.003551642819236627
Training Time:  0.31576817321436135 (+/-) 0.013597795949352978


=== Average network evolution ===
Total hidden node:  26.105545617173526 (+/-) 9.612601003243674
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=37, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=37, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 37
No. of parameters : 300
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:02:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  97.11878354203935 (+/-) 10.050885984568314
Testing Loss:  0.16422890465913176 (+/-) 0.25091905637381584
Precision:  0.9712158754269345
Recall:  0.9711878354203936
F1 score:  0.9711154125256082
Testing Time:  0.004337646880175432 (+/-) 0.0038182851119739343
Training Time:  0.31359051506506525 (+/-) 0.0138674977672068


=== Average network evolution ===
Total hidden node:  27.543828264758496 (+/-) 9.437552611661422
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=38, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=38, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 38
No. of parameters : 308
Voting weight:  [1.0]
N/A% (0 of 560) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--
Mean Accuracy:  97.24301075268818
Std Accuracy:  9.28754279400219
Hidden Node mean 27.877777777777776
Hidden Node std:  9.565007203534343
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (560 of 560) |######################| Elapsed Time: 0:01:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  95.01860465116278 (+/-) 13.261274712392677
Testing Loss:  0.29812649273595143 (+/-) 0.30080228160306777
Precision:  0.9504975087505442
Recall:  0.9501860465116279
F1 score:  0.9501623006284221
Testing Time:  0.003789654358128529 (+/-) 0.0037115292778900073
Training Time:  0.1604721840464365 (+/-) 0.010140744547632015


=== Average network evolution ===
Total hidden node:  17.547406082289804 (+/-) 6.7230537798450865
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=27, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=27, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 27
No. of parameters : 220
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:01:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  95.88050089445437 (+/-) 11.304858095741277
Testing Loss:  0.2592303505590542 (+/-) 0.2845174237879515
Precision:  0.9587814439468564
Recall:  0.9588050089445438
F1 score:  0.9587316285435442
Testing Time:  0.0038978149298052028 (+/-) 0.003781978613684488
Training Time:  0.15987096873506876 (+/-) 0.009208457808173295


=== Average network evolution ===
Total hidden node:  19.935599284436492 (+/-) 7.300070033511161
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=29, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=29, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 29
No. of parameters : 236
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:01:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  94.84579606440072 (+/-) 13.43551667949519
Testing Loss:  0.29246724934745344 (+/-) 0.3028206608801674
Precision:  0.9487262011808772
Recall:  0.9484579606440071
F1 score:  0.948393189447999
Testing Time:  0.0038992740173885774 (+/-) 0.003850099395327466
Training Time:  0.16123658983779934 (+/-) 0.009224956735775666


=== Average network evolution ===
Total hidden node:  19.561717352415027 (+/-) 6.6960085768371265
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=29, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=29, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 29
No. of parameters : 236
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:01:38 ETA:  00:00:00

=== Performance result ===
Accuracy:  94.73989266547404 (+/-) 13.575447451654385
Testing Loss:  0.28928095361547734 (+/-) 0.30191621277125724
Precision:  0.947470467436047
Recall:  0.9473989266547406
F1 score:  0.9472710209843055
Testing Time:  0.0038550049333111757 (+/-) 0.0035360793383130665
Training Time:  0.16794684747890412 (+/-) 0.018580007218041907


=== Average network evolution ===
Total hidden node:  18.220035778175312 (+/-) 6.878700578199054
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=27, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=27, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 27
No. of parameters : 220
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:01:42 ETA:  00:00:00

=== Performance result ===
Accuracy:  95.17459749552772 (+/-) 13.031784405913566
Testing Loss:  0.2735860873286967 (+/-) 0.2974053074192794
Precision:  0.951738021266323
Recall:  0.9517459749552772
F1 score:  0.9516377567739979
Testing Time:  0.004041421392096177 (+/-) 0.0036897660872174027
Training Time:  0.17515976228526325 (+/-) 0.020322992200329956


=== Average network evolution ===
Total hidden node:  20.125223613595708 (+/-) 7.067681280930563
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=29, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=29, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 29
No. of parameters : 236
Voting weight:  [1.0]
Mean Accuracy:  95.2426523297491
Std Accuracy:  12.691178382473245
Hidden Node mean 19.099283154121864
Hidden Node std:  6.998655748201287
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
100% (560 of 560) |######################| Elapsed Time: 0:00:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  28.906810035842295 (+/-) 2.054017010999749
Testing Loss:  1.3807804561003134 (+/-) 0.011864229444396562
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.26573461673729293
Recall:  0.28906810035842295
F1 score:  0.16936229501124764
Testing Time:  0.0029610976523395936 (+/-) 0.0038498457408812675
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  9.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=9, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=9, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 9
No. of parameters : 76
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:00:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  25.01541218637993 (+/-) 0.14899577341875636
Testing Loss:  1.3766053763341732 (+/-) 0.002995447889610214
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.06257708468544854
Recall:  0.25015412186379926
F1 score:  0.10011099206257089
Testing Time:  0.0027945870566966286 (+/-) 0.0038950997191526
Training Time:  1.7877120698224687e-06 (+/-) 4.2191519830838466e-05


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 5
No. of parameters : 44
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:00:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  41.80465949820788 (+/-) 5.036004397957265
Testing Loss:  1.3028935386288552 (+/-) 0.011201653772525988
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.5534162706599883
Recall:  0.41804659498207886
F1 score:  0.34071141256068216
Testing Time:  0.0026846047370664536 (+/-) 0.003532780724412595
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  8.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 8
No. of parameters : 68
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:00:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  41.11756272401434 (+/-) 3.671738399844149
Testing Loss:  1.3661051234464063 (+/-) 0.004718206055022647
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.21905520159042383
Recall:  0.4111756272401434
F1 score:  0.2835440709126196
Testing Time:  0.002659626759081331 (+/-) 0.003908108753083357
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  6.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 6
No. of parameters : 52
Voting weight:  [1.0]
100% (560 of 560) |######################| Elapsed Time: 0:00:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  25.010035842293906 (+/-) 0.11565459082289971
Testing Loss:  1.3951907897081 (+/-) 0.004390485498581702
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.0625501892832826
Recall:  0.2501003584229391
F1 score:  0.10007226837722473
Testing Time:  0.0029908222109613454 (+/-) 0.0037435923977363725
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  8.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=3, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=4, bias=True)
)
No. of inputs : 3
No. of nodes : 8
No. of parameters : 68
Voting weight:  [1.0]
Mean Accuracy:  32.36840215439857
Std Accuracy:  8.109569659857073
Hidden Node mean 7.2
Hidden Node std:  1.469693845669907
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [5]:
%run ADL_pmnist.ipynb
Number of input:  784
Number of output:  10
Number of batch:  138
All labeled
100% (138 of 138) |######################| Elapsed Time: 0:01:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.21605839416058 (+/-) 12.653635313755666
Testing Loss:  0.5299952784757109 (+/-) 0.3892834901103308
Precision:  0.8416550147546307
Recall:  0.8421605839416059
F1 score:  0.8416725795317286
Testing Time:  0.003857189721434656 (+/-) 0.004000561553988171
Training Time:  0.6990314017247109 (+/-) 0.033090851766374926


=== Average network evolution ===
Total hidden node:  17.56934306569343 (+/-) 2.4518594773976075
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 20
No. of parameters : 15910
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.74598540145986 (+/-) 12.917492325160863
Testing Loss:  0.5100546096907045 (+/-) 0.40021389069832347
Precision:  0.8472381593398333
Recall:  0.8474598540145986
F1 score:  0.8471865724310298
Testing Time:  0.004004248737418738 (+/-) 0.004329616346014479
Training Time:  0.6855113732553747 (+/-) 0.019572027733594493


=== Average network evolution ===
Total hidden node:  22.014598540145986 (+/-) 4.60241986724923
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=30, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=30, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 30
No. of parameters : 23860
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:35 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.58540145985403 (+/-) 12.4274862550659
Testing Loss:  0.5213972165038551 (+/-) 0.3966300492360766
Precision:  0.8453992297654769
Recall:  0.8458540145985401
F1 score:  0.8454436146001473
Testing Time:  0.004104240097268654 (+/-) 0.003651723519130708
Training Time:  0.6909720723646401 (+/-) 0.028694711395282294


=== Average network evolution ===
Total hidden node:  23.197080291970803 (+/-) 6.9511742599429445
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=36, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=36, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 36
No. of parameters : 28630
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.25255474452555 (+/-) 12.124446441074227
Testing Loss:  0.5319883200156428 (+/-) 0.3924745387530294
Precision:  0.8419088124333297
Recall:  0.8425255474452554
F1 score:  0.8420690044013521
Testing Time:  0.003943894031274058 (+/-) 0.0035111099992132188
Training Time:  0.6999243854606239 (+/-) 0.03308558338599792


=== Average network evolution ===
Total hidden node:  18.204379562043794 (+/-) 2.546326067076693
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=21, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=21, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 21
No. of parameters : 16705
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.44671532846716 (+/-) 12.7199656331015
Testing Loss:  0.5224682564174172 (+/-) 0.381670897769678
Precision:  0.8441187917103862
Recall:  0.8444671532846715
F1 score:  0.844042617245612
Testing Time:  0.0038340770415145986 (+/-) 0.0035691532330264994
Training Time:  0.6770647616281996 (+/-) 0.022852488245372768


=== Average network evolution ===
Total hidden node:  17.605839416058394 (+/-) 1.9756091705220327
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 20
No. of parameters : 15910
Voting weight:  [1.0]
Mean Accuracy:  84.70382352941178
Std Accuracy:  12.255283977967334
Hidden Node mean 19.764705882352942
Hidden Node std:  4.774988903771596
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (138 of 138) |######################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  80.88613138686131 (+/-) 14.290965869100262
Testing Loss:  0.6502768283669096 (+/-) 0.433513438047007
Precision:  0.8072198139913351
Recall:  0.8088613138686132
F1 score:  0.8071815540058104
Testing Time:  0.003489384685989714 (+/-) 0.0037670206135806553
Training Time:  0.33638614285601315 (+/-) 0.016971683304853734


=== Average network evolution ===
Total hidden node:  15.211678832116789 (+/-) 1.9005594909402377
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=17, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=17, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 17
No. of parameters : 13525
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  81.83795620437955 (+/-) 14.012310184220583
Testing Loss:  0.617952929959245 (+/-) 0.410199837927235
Precision:  0.8173447148396881
Recall:  0.8183795620437956
F1 score:  0.8173417712267829
Testing Time:  0.003627864113689339 (+/-) 0.003503028857547654
Training Time:  0.33586348582358255 (+/-) 0.012826728466561556


=== Average network evolution ===
Total hidden node:  18.474452554744527 (+/-) 1.9145249338155677
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 20
No. of parameters : 15910
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  81.88175182481751 (+/-) 13.50954363381249
Testing Loss:  0.6170137628477855 (+/-) 0.4044168899260186
Precision:  0.81778940535475
Recall:  0.8188175182481752
F1 score:  0.817702378637757
Testing Time:  0.003910365765982301 (+/-) 0.004675826452204106
Training Time:  0.33516328526239325 (+/-) 0.010340495500602464


=== Average network evolution ===
Total hidden node:  18.1021897810219 (+/-) 2.411301467445096
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 20
No. of parameters : 15910
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:47 ETA:  00:00:00

=== Performance result ===
Accuracy:  81.10218978102189 (+/-) 14.250339820014153
Testing Loss:  0.6383997452628873 (+/-) 0.41971078258978967
Precision:  0.8097897103781534
Recall:  0.8110218978102189
F1 score:  0.8100443431849681
Testing Time:  0.0035352063004987955 (+/-) 0.003258019551746477
Training Time:  0.3381819672828173 (+/-) 0.014580208957045619


=== Average network evolution ===
Total hidden node:  16.583941605839417 (+/-) 2.2201543175352505
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=19, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=19, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 19
No. of parameters : 15115
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:46 ETA:  00:00:00

=== Performance result ===
Accuracy:  81.20729927007298 (+/-) 14.175158877501453
Testing Loss:  0.6442732809886446 (+/-) 0.4113639593405351
Precision:  0.8110618715073876
Recall:  0.81207299270073
F1 score:  0.8109622671410924
Testing Time:  0.0035519443289206845 (+/-) 0.003577710137397939
Training Time:  0.3305896024634368 (+/-) 0.009684010989262899


=== Average network evolution ===
Total hidden node:  15.138686131386862 (+/-) 1.500279690478304
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=16, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=16, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 16
No. of parameters : 12730
Voting weight:  [1.0]
N/A% (0 of 138) |                        | Elapsed Time: 0:00:00 ETA:  --:--:--
Mean Accuracy:  81.73029411764706
Std Accuracy:  13.494134670356974
Hidden Node mean 16.726470588235294
Hidden Node std:  2.442612972103417
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (138 of 138) |######################| Elapsed Time: 0:00:23 ETA:  00:00:00

=== Performance result ===
Accuracy:  74.95182481751824 (+/-) 17.048244562283898
Testing Loss:  0.8686235523136863 (+/-) 0.48007725273905405
Precision:  0.746902668866979
Recall:  0.7495182481751825
F1 score:  0.7462196258098396
Testing Time:  0.00334940165498831 (+/-) 0.004532571562757123
Training Time:  0.169146341128941 (+/-) 0.009097344356041301


=== Average network evolution ===
Total hidden node:  13.510948905109489 (+/-) 1.3019737308907036
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=15, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=15, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 15
No. of parameters : 11935
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  78.33284671532847 (+/-) 15.913860778859181
Testing Loss:  0.7683567316645253 (+/-) 0.4606781109564946
Precision:  0.7823958145795648
Recall:  0.7833284671532846
F1 score:  0.7818418313450543
Testing Time:  0.0034434882393718637 (+/-) 0.0033551168808069287
Training Time:  0.17254897799805133 (+/-) 0.012978697164451361


=== Average network evolution ===
Total hidden node:  18.072992700729927 (+/-) 1.3270627051139614
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 20
No. of parameters : 15910
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.16934306569344 (+/-) 15.722908861660649
Testing Loss:  0.7864098247602909 (+/-) 0.448316591996406
Precision:  0.7692460019539521
Recall:  0.7716934306569343
F1 score:  0.7691168634308589
Testing Time:  0.0037644153093769604 (+/-) 0.00496851830327111
Training Time:  0.17065287854549657 (+/-) 0.008547987984671731


=== Average network evolution ===
Total hidden node:  16.956204379562045 (+/-) 1.0454532292643988
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=18, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=18, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 18
No. of parameters : 14320
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.32262773722628 (+/-) 17.106591518679807
Testing Loss:  0.8652569673357219 (+/-) 0.48437066011097796
Precision:  0.7507739176934152
Recall:  0.7532262773722628
F1 score:  0.7507158147571324
Testing Time:  0.0033046851192947723 (+/-) 0.0031900432097960174
Training Time:  0.17169494350461195 (+/-) 0.011608721505436966


=== Average network evolution ===
Total hidden node:  12.985401459854014 (+/-) 0.7544070176761591
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=14, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=14, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 14
No. of parameters : 11140
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  73.54014598540147 (+/-) 18.02475775009171
Testing Loss:  0.9113261250466326 (+/-) 0.50209809040161
Precision:  0.7327828379796012
Recall:  0.7354014598540146
F1 score:  0.7321587060237189
Testing Time:  0.0032818717678097914 (+/-) 0.00318632995556695
Training Time:  0.17031842078605708 (+/-) 0.009504997955329752


=== Average network evolution ===
Total hidden node:  12.167883211678832 (+/-) 1.3211880467872947
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=14, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=14, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 14
No. of parameters : 11140
Voting weight:  [1.0]
Mean Accuracy:  76.22882352941176
Std Accuracy:  16.379825964152275
Hidden Node mean 14.745588235294118
Hidden Node std:  2.611903397880862
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
 91% (126 of 138) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  25.333823529411763 (+/-) 25.502007477463867
Testing Loss:  2.064229090424145 (+/-) 0.4104954158584063
Precision:  0.4374358587116846
Recall:  0.25333823529411764
F1 score:  0.2646958627693986
Testing Time:  0.0027500513721914854 (+/-) 0.004273491811467424
Training Time:  7.338383618523093e-06 (+/-) 8.526431262786378e-05


=== Average network evolution ===
Total hidden node:  14.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=14, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=14, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 14
No. of parameters : 11140
Voting weight:  [1.0]
 91% (126 of 138) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  22.43235294117647 (+/-) 23.74488453377888
Testing Loss:  2.1428030466332153 (+/-) 0.37636946841250846
Precision:  0.47727134531972476
Recall:  0.2243235294117647
F1 score:  0.23373218858229994
Testing Time:  0.002472253406749052 (+/-) 0.003273756324019873
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  12.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=12, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=12, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 12
No. of parameters : 9550
Voting weight:  [1.0]
 91% (126 of 138) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  19.908823529411762 (+/-) 21.856831852213094
Testing Loss:  2.1821167635567047 (+/-) 0.38966945128539
Precision:  0.5288993945686016
Recall:  0.19908823529411765
F1 score:  0.19795959330194587
Testing Time:  0.002552656566395479 (+/-) 0.002942262730630038
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  13.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 13
No. of parameters : 10345
Voting weight:  [1.0]
 99% (137 of 138) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  22.325000000000003 (+/-) 24.809852614731632
Testing Loss:  2.1229126427103493 (+/-) 0.3791066752811218
Precision:  0.519875513686255
Recall:  0.22325
F1 score:  0.23257330587375025
Testing Time:  0.002714463893105002 (+/-) 0.003269130798608319
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  13.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 13
No. of parameters : 10345
Voting weight:  [1.0]
 96% (133 of 138) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  23.805882352941175 (+/-) 25.919308509935558
Testing Loss:  2.127225234228022 (+/-) 0.41781618269887444
Precision:  0.6289586207790309
Recall:  0.23805882352941177
F1 score:  0.2664406448968325
Testing Time:  0.0027649385087630328 (+/-) 0.0035959664330713543
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  15.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=15, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=15, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 15
No. of parameters : 11935
Voting weight:  [1.0]
Mean Accuracy:  22.64474074074074
Std Accuracy:  24.526693812604037
Hidden Node mean 13.4
Hidden Node std:  1.019803902718557
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [6]:
%run ADL_rmnist.ipynb
Number of input:  784
Number of output:  10
Number of batch:  138
All labeled
100% (138 of 138) |######################| Elapsed Time: 0:01:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.20875912408759 (+/-) 5.263390631710589
Testing Loss:  0.38442177736084826 (+/-) 0.20877860168352383
Precision:  0.8917050037765241
Recall:  0.8920875912408759
F1 score:  0.8917881746379951
Testing Time:  0.0037725180605032147 (+/-) 0.0029109260512575064
Training Time:  0.7038712605942775 (+/-) 0.03201929995692592


=== Average network evolution ===
Total hidden node:  18.693430656934307 (+/-) 2.832455394010672
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=23, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=23, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 23
No. of parameters : 18295
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  88.97518248175183 (+/-) 6.084007767429762
Testing Loss:  0.39315680852227836 (+/-) 0.22934648708743813
Precision:  0.8893695798676612
Recall:  0.8897518248175182
F1 score:  0.8893514530366471
Testing Time:  0.003854205138491888 (+/-) 0.003653415689521969
Training Time:  0.6866993782294057 (+/-) 0.01641039802917066


=== Average network evolution ===
Total hidden node:  18.78102189781022 (+/-) 3.1454180056357246
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=24, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=24, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 24
No. of parameters : 19090
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.02773722627737 (+/-) 5.80707760877256
Testing Loss:  0.3852812723413001 (+/-) 0.19998946979281998
Precision:  0.8897281753500507
Recall:  0.8902773722627737
F1 score:  0.889828165551493
Testing Time:  0.003944682378838532 (+/-) 0.0038287393661166147
Training Time:  0.6830965880929989 (+/-) 0.02386645554321748


=== Average network evolution ===
Total hidden node:  20.233576642335766 (+/-) 3.989516871986278
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=28, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=28, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 28
No. of parameters : 22270
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:33 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.48905109489051 (+/-) 5.017744845361881
Testing Loss:  0.37946582340846097 (+/-) 0.21104281442560785
Precision:  0.894456103077244
Recall:  0.8948905109489051
F1 score:  0.8945418150721977
Testing Time:  0.003903547342676316 (+/-) 0.0042483712992618106
Training Time:  0.6733669608178801 (+/-) 0.017356437949479744


=== Average network evolution ===
Total hidden node:  20.72992700729927 (+/-) 4.318528489640881
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=28, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=28, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 28
No. of parameters : 22270
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:01:42 ETA:  00:00:00

=== Performance result ===
Accuracy:  89.83357664233577 (+/-) 5.785588405083019
Testing Loss:  0.36382242066472986 (+/-) 0.22140838424531714
Precision:  0.8979836238111282
Recall:  0.8983357664233577
F1 score:  0.8980156337447938
Testing Time:  0.004454988632759039 (+/-) 0.00500682282650324
Training Time:  0.7452280416975926 (+/-) 0.07224029757590479


=== Average network evolution ===
Total hidden node:  26.094890510948904 (+/-) 7.721316792957612
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=37, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=37, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 37
No. of parameters : 29425
Voting weight:  [1.0]
Mean Accuracy:  89.625
Std Accuracy:  4.2059088337298824
Hidden Node mean 20.96323529411765
Hidden Node std:  5.436813632454992
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (138 of 138) |######################| Elapsed Time: 0:00:49 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.60875912408758 (+/-) 8.016401748937795
Testing Loss:  0.49998656692948656 (+/-) 0.2970231421724114
Precision:  0.8657618305244025
Recall:  0.8660875912408759
F1 score:  0.86545540083863
Testing Time:  0.0037748413364382554 (+/-) 0.004041462608065304
Training Time:  0.35309866571078335 (+/-) 0.024523129108556117


=== Average network evolution ===
Total hidden node:  15.540145985401459 (+/-) 2.106696305060119
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=18, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=18, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 18
No. of parameters : 14320
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.8029197080292 (+/-) 7.661868248145967
Testing Loss:  0.4811633670308294 (+/-) 0.2872784448016916
Precision:  0.8677312527129786
Recall:  0.868029197080292
F1 score:  0.8674457213423348
Testing Time:  0.004164881949877217 (+/-) 0.004627601071256578
Training Time:  0.372638042825852 (+/-) 0.03479158438549361


=== Average network evolution ===
Total hidden node:  18.21897810218978 (+/-) 2.993216975234898
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=22, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=22, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 22
No. of parameters : 17500
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:52 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.66715328467154 (+/-) 7.434866660618423
Testing Loss:  0.4840749332504551 (+/-) 0.2797381019945645
Precision:  0.8660293086155019
Recall:  0.8666715328467153
F1 score:  0.8659433644128327
Testing Time:  0.0040364369858790486 (+/-) 0.004661190528711577
Training Time:  0.37548991189385855 (+/-) 0.03650414882442444


=== Average network evolution ===
Total hidden node:  16.802919708029197 (+/-) 1.8076860074643484
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=19, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=19, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 19
No. of parameters : 15115
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:51 ETA:  00:00:00

=== Performance result ===
Accuracy:  87.61605839416058 (+/-) 6.081397188394578
Testing Loss:  0.4593784056440757 (+/-) 0.2609606645720423
Precision:  0.8756213963317653
Recall:  0.8761605839416058
F1 score:  0.8756129641498354
Testing Time:  0.0039273004462249085 (+/-) 0.004855012372046954
Training Time:  0.371994711186764 (+/-) 0.03443739223074941


=== Average network evolution ===
Total hidden node:  19.233576642335766 (+/-) 2.572348109970825
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=24, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=24, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 24
No. of parameters : 19090
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:48 ETA:  00:00:00

=== Performance result ===
Accuracy:  86.52846715328467 (+/-) 7.175698535696609
Testing Loss:  0.49342357345523624 (+/-) 0.2879587840061541
Precision:  0.8645745908058169
Recall:  0.8652846715328467
F1 score:  0.8644812637844438
Testing Time:  0.0035975518887930544 (+/-) 0.0031893891031047543
Training Time:  0.3496038008780375 (+/-) 0.018651515103250214


=== Average network evolution ===
Total hidden node:  16.613138686131386 (+/-) 2.3154453629790837
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=20, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=20, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 20
No. of parameters : 15910
Voting weight:  [1.0]
Mean Accuracy:  87.21794117647059
Std Accuracy:  5.86720460516699
Hidden Node mean 17.30735294117647
Hidden Node std:  2.7129220287829976
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (138 of 138) |######################| Elapsed Time: 0:00:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.65401459854016 (+/-) 10.068393957116463
Testing Loss:  0.623548363247057 (+/-) 0.37014799204740256
Precision:  0.8351284807501452
Recall:  0.8365401459854015
F1 score:  0.8351441654546017
Testing Time:  0.00333879289835909 (+/-) 0.00328189061858016
Training Time:  0.1776188220420893 (+/-) 0.015539172806005008


=== Average network evolution ===
Total hidden node:  14.481751824817518 (+/-) 1.4802948501965978
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=17, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=17, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 17
No. of parameters : 13525
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.23503649635036 (+/-) 9.172281245515926
Testing Loss:  0.6137293473864994 (+/-) 0.3403226259591167
Precision:  0.8417307021005614
Recall:  0.8423503649635037
F1 score:  0.8408539939216325
Testing Time:  0.003154963472463789 (+/-) 0.00330497857154288
Training Time:  0.17120972515022667 (+/-) 0.00904131677153224


=== Average network evolution ===
Total hidden node:  14.81021897810219 (+/-) 1.645754754260998
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=17, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=17, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 17
No. of parameters : 13525
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.43065693430657 (+/-) 9.32986384801257
Testing Loss:  0.5893517212711111 (+/-) 0.3460455462884988
Precision:  0.843721267303986
Recall:  0.8443065693430657
F1 score:  0.8434313176093274
Testing Time:  0.0031467510835967794 (+/-) 0.0034525257244636203
Training Time:  0.17096437502951517 (+/-) 0.008614652568017281


=== Average network evolution ===
Total hidden node:  16.78832116788321 (+/-) 1.568069420360645
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=19, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=19, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 19
No. of parameters : 15115
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.46861313868612 (+/-) 9.81824424092342
Testing Loss:  0.5969956469361799 (+/-) 0.3436997668214151
Precision:  0.8443987247139246
Recall:  0.8446861313868613
F1 score:  0.8438607695163073
Testing Time:  0.003366546909304431 (+/-) 0.0041205711683533425
Training Time:  0.1728711824347503 (+/-) 0.010298479654915682


=== Average network evolution ===
Total hidden node:  17.59124087591241 (+/-) 1.9873862985446562
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=21, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=21, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 21
No. of parameters : 16705
Voting weight:  [1.0]
100% (138 of 138) |######################| Elapsed Time: 0:00:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.71970802919707 (+/-) 10.009002075256568
Testing Loss:  0.6140992701814992 (+/-) 0.35692050239663226
Precision:  0.8361368785000315
Recall:  0.8371970802919708
F1 score:  0.8360610360382664
Testing Time:  0.0031542464764448847 (+/-) 0.0035443633346721125
Training Time:  0.17139535750785884 (+/-) 0.008651194137348928


=== Average network evolution ===
Total hidden node:  15.875912408759124 (+/-) 1.6453662227377572
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=18, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=18, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 18
No. of parameters : 14320
Voting weight:  [1.0]
Mean Accuracy:  84.52029411764707
Std Accuracy:  8.40162798835269
Hidden Node mean 15.923529411764706
Hidden Node std:  2.040769581415076
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
 91% (126 of 138) |####################  | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  52.87352941176471 (+/-) 4.982074268198019
Testing Loss:  1.70448217847768 (+/-) 0.06028631635758112
Precision:  0.6194206399526673
Recall:  0.5287352941176471
F1 score:  0.4966379150300731
Testing Time:  0.002354104729259715 (+/-) 0.004393785955882732
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  12.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=12, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=12, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 12
No. of parameters : 9550
Voting weight:  [1.0]
 99% (137 of 138) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  60.35588235294117 (+/-) 5.100616524238578
Testing Loss:  1.5087173546061796 (+/-) 0.07931457074769332
Precision:  0.6406761426868426
Recall:  0.6035588235294118
F1 score:  0.5719097962441663
Testing Time:  0.0023840245078591738 (+/-) 0.002936071570207057
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  13.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 13
No. of parameters : 10345
Voting weight:  [1.0]
 97% (135 of 138) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  62.89852941176471 (+/-) 6.396506230358671
Testing Loss:  1.5400805245427525 (+/-) 0.07778116809315058
Precision:  0.6884096134990224
Recall:  0.628985294117647
F1 score:  0.6289849014294346
Testing Time:  0.0022737874704248763 (+/-) 0.002949484099497785
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  13.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 13
No. of parameters : 10345
Voting weight:  [1.0]
 95% (132 of 138) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  56.56029411764706 (+/-) 4.441834534417268
Testing Loss:  1.600654026164728 (+/-) 0.060454918549738036
Precision:  0.6682785836902212
Recall:  0.5656029411764706
F1 score:  0.5422914345961902
Testing Time:  0.0027360442806692686 (+/-) 0.004016387755502349
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  11.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=11, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=11, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 11
No. of parameters : 8755
Voting weight:  [1.0]
 95% (132 of 138) |##################### | Elapsed Time: 0:00:01 ETA:   0:00:00

=== Performance result ===
Accuracy:  63.74558823529413 (+/-) 5.6033848442528695
Testing Loss:  1.4753911109531628 (+/-) 0.0806018255153356
Precision:  0.6981774536065212
Recall:  0.6374558823529411
F1 score:  0.6289148080096935
Testing Time:  0.0022810329409206614 (+/-) 0.0030429463503291814
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  13.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=784, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=10, bias=True)
)
No. of inputs : 784
No. of nodes : 13
No. of parameters : 10345
Voting weight:  [1.0]
Mean Accuracy:  59.255111111111106
Std Accuracy:  6.705914456012545
Hidden Node mean 12.4
Hidden Node std:  0.8
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [7]:
%run ADL_hepmass.ipynb
Number of input:  28
Number of output:  2
Number of batch:  4000
All labeled
100% (4000 of 4000) |####################| Elapsed Time: 0:49:06 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.27471867966993 (+/-) 1.9651778534340254
Testing Loss:  0.330267546474412 (+/-) 0.0298085893511028
Precision:  0.8444971813332426
Recall:  0.8427471867966991
F1 score:  0.8425459401381118
Testing Time:  0.008208171461009479 (+/-) 0.005566143633784638
Training Time:  0.7113397854153709 (+/-) 0.07011717912570137


=== Average network evolution ===
Total hidden node:  3.8547136784196048 (+/-) 0.5520175202166179
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 3
No. of parameters : 95
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:48:01 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.34248562140534 (+/-) 1.96683502949259
Testing Loss:  0.329345764480969 (+/-) 0.029565521804856314
Precision:  0.8449849427140919
Recall:  0.8434248562140535
F1 score:  0.843246431985762
Testing Time:  0.009227581756297992 (+/-) 0.006537240098537969
Training Time:  0.6939987721935634 (+/-) 0.059228153575059346


=== Average network evolution ===
Total hidden node:  6.903725931482871 (+/-) 0.3301679476018715
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 7
No. of parameters : 219
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:51:36 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.38789697424355 (+/-) 2.1638401291256364
Testing Loss:  0.32911720091281876 (+/-) 0.031897747793727456
Precision:  0.8453157754901114
Recall:  0.8438789697424356
F1 score:  0.843715246793188
Testing Time:  0.009940651304336095 (+/-) 0.006515943899486795
Training Time:  0.7462876080930099 (+/-) 0.05905850252163256


=== Average network evolution ===
Total hidden node:  7.434858714678669 (+/-) 0.5193867676857585
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 7
No. of parameters : 219
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:49:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.25331332833208 (+/-) 1.8797451316707565
Testing Loss:  0.33065941628738477 (+/-) 0.029332341065045873
Precision:  0.8442250768667071
Recall:  0.8425331332833208
F1 score:  0.8423381302472389
Testing Time:  0.008174278581699869 (+/-) 0.005233628019318262
Training Time:  0.7157893950535554 (+/-) 0.029865859339877104


=== Average network evolution ===
Total hidden node:  3.4466116529132282 (+/-) 0.5460425236038302
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 3
No. of parameters : 95
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:49:37 ETA:  00:00:00

=== Performance result ===
Accuracy:  84.35663915978995 (+/-) 2.054844496319103
Testing Loss:  0.3273094044041115 (+/-) 0.03136871028044463
Precision:  0.8451452268971658
Recall:  0.8435663915978995
F1 score:  0.8433860750777953
Testing Time:  0.00952579510691882 (+/-) 0.006281172256604657
Training Time:  0.7174528066025104 (+/-) 0.01771030362514928


=== Average network evolution ===
Total hidden node:  7.910227556889223 (+/-) 0.3379666826781271
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 8
No. of parameters : 250
Voting weight:  [1.0]
Mean Accuracy:  84.33150575287644
Std Accuracy:  1.9333762840610735
Hidden Node mean 5.910505252626313
Hidden Node std:  1.9339634955832405
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (4000 of 4000) |####################| Elapsed Time: 0:25:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.73608402100524 (+/-) 2.2802007801598734
Testing Loss:  0.33798245888526635 (+/-) 0.0355996361254071
Precision:  0.8393397048267965
Recall:  0.8373608402100525
F1 score:  0.8371219459925799
Testing Time:  0.009206158305800358 (+/-) 0.006176437594693677
Training Time:  0.3548685260104012 (+/-) 0.011513308116532955


=== Average network evolution ===
Total hidden node:  4.911477869467367 (+/-) 0.41858045086497236
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 5
No. of parameters : 157
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:25:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.80280070017506 (+/-) 2.491406015490654
Testing Loss:  0.3377445449111282 (+/-) 0.036908027711822125
Precision:  0.8395329339693653
Recall:  0.8380280070017504
F1 score:  0.8378470796771735
Testing Time:  0.00933564195158363 (+/-) 0.006164510772438725
Training Time:  0.3493382015595528 (+/-) 0.009825766971749281


=== Average network evolution ===
Total hidden node:  7.700925231307827 (+/-) 0.5802247920964608
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 8
No. of parameters : 250
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:24:57 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.79224806201549 (+/-) 2.80505204973652
Testing Loss:  0.33820619355681303 (+/-) 0.03975921309941251
Precision:  0.8394859528110324
Recall:  0.8379224806201551
F1 score:  0.8377343826954374
Testing Time:  0.009186149090640274 (+/-) 0.00626325328826033
Training Time:  0.3481195026649538 (+/-) 0.00944403192134


=== Average network evolution ===
Total hidden node:  5.782945736434108 (+/-) 0.5481554007688418
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 6
No. of parameters : 188
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:25:01 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.79674918729683 (+/-) 2.210298801080123
Testing Loss:  0.3376355614773063 (+/-) 0.034171457758005105
Precision:  0.8395973502428108
Recall:  0.8379674918729683
F1 score:  0.8377715437863407
Testing Time:  0.009212620409168759 (+/-) 0.006194103125854386
Training Time:  0.3490182176534162 (+/-) 0.010273933757171458


=== Average network evolution ===
Total hidden node:  5.91297824456114 (+/-) 0.39870897844065606
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 6
No. of parameters : 188
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:25:03 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.99159789947487 (+/-) 2.3756347220140346
Testing Loss:  0.33507401953938304 (+/-) 0.036372755866008466
Precision:  0.8412093828703266
Recall:  0.8399159789947487
F1 score:  0.839762991287483
Testing Time:  0.009374589555172301 (+/-) 0.006435902762300744
Training Time:  0.349297381604007 (+/-) 0.011187877916816044


=== Average network evolution ===
Total hidden node:  6.961740435108777 (+/-) 0.22427471197065021
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 7
No. of parameters : 219
Voting weight:  [1.0]
Mean Accuracy:  83.83330665332666
Std Accuracy:  2.369747048114372
Hidden Node mean 6.254627313656829
Hidden Node std:  1.0722743281416995
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (4000 of 4000) |####################| Elapsed Time: 0:13:23 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.3966991747937 (+/-) 2.6304446234441183
Testing Loss:  0.3441671575343916 (+/-) 0.04142407049523018
Precision:  0.8357253163748376
Recall:  0.833966991747937
F1 score:  0.8337479100156516
Testing Time:  0.008493842110391794 (+/-) 0.005826768953672994
Training Time:  0.17510843724124162 (+/-) 0.007163980227652877


=== Average network evolution ===
Total hidden node:  4.340585146286571 (+/-) 0.5464479929889785
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 5
No. of parameters : 157
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:13:32 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.35513878469618 (+/-) 2.313399215110903
Testing Loss:  0.34491376737917506 (+/-) 0.03777271849745239
Precision:  0.8348697876299853
Recall:  0.8335513878469617
F1 score:  0.8333861772989148
Testing Time:  0.009001937321526732 (+/-) 0.006135936037090921
Training Time:  0.17680245615536347 (+/-) 0.008211680116700596


=== Average network evolution ===
Total hidden node:  6.323580895223806 (+/-) 0.4867040174430941
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 6
No. of parameters : 188
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:13:29 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.3375343835959 (+/-) 2.881361584980513
Testing Loss:  0.3472857065619931 (+/-) 0.047013739008987976
Precision:  0.8353999425426777
Recall:  0.833375343835959
F1 score:  0.8331220002570955
Testing Time:  0.008857515282140847 (+/-) 0.0060651115955736344
Training Time:  0.17625329124238914 (+/-) 0.007162263950789549


=== Average network evolution ===
Total hidden node:  4.516129032258065 (+/-) 0.7048415564932156
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 5
No. of parameters : 157
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:13:27 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.27941985496375 (+/-) 2.8541707440471957
Testing Loss:  0.351626099661369 (+/-) 0.046221010121858364
Precision:  0.8348148363568347
Recall:  0.8327941985496374
F1 score:  0.8325400236600833
Testing Time:  0.007976404694683345 (+/-) 0.00507851170744298
Training Time:  0.17676449143967052 (+/-) 0.00844617077029112


=== Average network evolution ===
Total hidden node:  3.7881970492623154 (+/-) 0.5375620600669296
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 126
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:13:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  83.60165041260315 (+/-) 2.340824030358643
Testing Loss:  0.34333790804809794 (+/-) 0.03818323402283034
Precision:  0.8377873330871999
Recall:  0.8360165041260315
F1 score:  0.835799923710361
Testing Time:  0.00800256462030394 (+/-) 0.00506383917022807
Training Time:  0.17630566081633475 (+/-) 0.007307652848869432


=== Average network evolution ===
Total hidden node:  3.7496874218554637 (+/-) 0.4885375569549067
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 126
Voting weight:  [1.0]
Mean Accuracy:  83.40190095047524
Std Accuracy:  2.5701554890342733
Hidden Node mean 4.543721860930465
Hidden Node std:  1.0929142626345736
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
100% (4000 of 4000) |####################| Elapsed Time: 0:01:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  51.88724362181091 (+/-) 2.280085908919687
Testing Loss:  0.6889360942293132 (+/-) 0.008801739019871982
Precision:  0.6739113752749148
Recall:  0.5188724362181091
F1 score:  0.3807828713531886
Testing Time:  0.008792701752678402 (+/-) 0.00621113491233278
Training Time:  4.990211780695035e-07 (+/-) 2.2305746833386594e-05


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 5
No. of parameters : 157
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:42 ETA:  00:00:00

=== Performance result ===
Accuracy:  59.94467233616808 (+/-) 2.2054052431091344
Testing Loss:  0.6553475126557019 (+/-) 0.006080473222214076
Precision:  0.7336454548725878
Recall:  0.5994467233616808
F1 score:  0.5322370776305818
Testing Time:  0.008687302910011371 (+/-) 0.006240351162555132
Training Time:  1.9982911873722505e-06 (+/-) 4.46273008904126e-05


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 126
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:41 ETA:  00:00:00

=== Performance result ===
Accuracy:  62.241570785392696 (+/-) 2.1551531445364005
Testing Loss:  0.6735364650415742 (+/-) 0.003394087776875502
Precision:  0.6258176963079225
Recall:  0.622415707853927
F1 score:  0.6198328196016225
Testing Time:  0.008753573077508603 (+/-) 0.00636426305167349
Training Time:  2.494390276803441e-06 (+/-) 4.981293326105004e-05


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 126
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  50.008404202101055 (+/-) 2.2817827834914235
Testing Loss:  0.7205007633994733 (+/-) 0.013804003489672229
C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))
Precision:  0.25008404908407184
Recall:  0.5000840420210105
F1 score:  0.3334267175419617
Testing Time:  0.008766726114083195 (+/-) 0.006287377636701752
Training Time:  1.9518359414692697e-06 (+/-) 4.3667603728757356e-05


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 4
No. of parameters : 126
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  50.26663331665833 (+/-) 2.2788678857122937
Testing Loss:  0.6920883044891205 (+/-) 0.007213508815540086
Precision:  0.6718153910764981
Recall:  0.5026663331665833
F1 score:  0.34017623353104365
Testing Time:  0.008905775431336731 (+/-) 0.006393594466951613
Training Time:  9.97147839208911e-07 (+/-) 3.150893875173259e-05


=== Average network evolution ===
Total hidden node:  6.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=28, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 28
No. of nodes : 6
No. of parameters : 188
Voting weight:  [1.0]
Mean Accuracy:  54.87060295221416
Std Accuracy:  5.637552435216559
Hidden Node mean 4.6
Hidden Node std:  0.7999999999999999
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [8]:
%run ADL_susy.ipynb
Number of input:  18
Number of output:  2
Number of batch:  4000
All labeled
100% (4000 of 4000) |####################| Elapsed Time: 0:47:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.98624656164041 (+/-) 2.870595926016961
Testing Loss:  0.46739256575752064 (+/-) 0.03808193857755734
Precision:  0.7820258498962392
Recall:  0.7798624656164042
F1 score:  0.7777780905095765
Testing Time:  0.01032141984537501 (+/-) 0.00653900627634962
Training Time:  0.684944398703054 (+/-) 0.021504909906513797


=== Average network evolution ===
Total hidden node:  13.223055763940986 (+/-) 2.179207608533761
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=15, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=15, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 15
No. of parameters : 317
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:46:34 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.67516879219805 (+/-) 3.2094666588585863
Testing Loss:  0.4738897577721824 (+/-) 0.04163854025241314
Precision:  0.7802283674036524
Recall:  0.7767516879219805
F1 score:  0.7740490196201357
Testing Time:  0.009990863664116254 (+/-) 0.006582541361882863
Training Time:  0.6713744699731413 (+/-) 0.015871658745390784


=== Average network evolution ===
Total hidden node:  7.553138284571143 (+/-) 2.5114122175508693
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=10, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=10, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 10
No. of parameters : 212
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:46:31 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.78319579894973 (+/-) 3.1024061501361255
Testing Loss:  0.472243248536963 (+/-) 0.039934397161484524
Precision:  0.780261644734397
Recall:  0.7778319579894973
F1 score:  0.7755870941501782
Testing Time:  0.010030536181809277 (+/-) 0.006650525102604511
Training Time:  0.670523231403325 (+/-) 0.04033957599114281


=== Average network evolution ===
Total hidden node:  9.486871717929482 (+/-) 1.933701112192794
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=11, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 11
No. of parameters : 233
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:47:00 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.80165041260317 (+/-) 3.0552677365584047
Testing Loss:  0.4695698034393695 (+/-) 0.03943318144787431
Precision:  0.7798153969026214
Recall:  0.7780165041260315
F1 score:  0.7760571855446129
Testing Time:  0.010456002572382292 (+/-) 0.006981026421497293
Training Time:  0.6769910026830743 (+/-) 0.05434663596325156


=== Average network evolution ===
Total hidden node:  10.490372593148287 (+/-) 2.4437343954812203
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 13
No. of parameters : 275
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:45:13 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.60495123780946 (+/-) 2.903258982514776
Testing Loss:  0.47470015815032307 (+/-) 0.038621717103126424
Precision:  0.7791097126541696
Recall:  0.7760495123780945
F1 score:  0.7734965691343383
Testing Time:  0.007933711612126207 (+/-) 0.0054821416210230674
Training Time:  0.6528648394708426 (+/-) 0.030866081476768156


=== Average network evolution ===
Total hidden node:  4.51937984496124 (+/-) 1.3209838246814924
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 7
No. of parameters : 149
Voting weight:  [1.0]
Mean Accuracy:  77.776008004002
Std Accuracy:  3.011797492196806
Hidden Node mean 9.05552776388194
Hidden Node std:  3.6043048866546425
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
50% labeled
100% (4000 of 4000) |####################| Elapsed Time: 0:24:05 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.2339584896224 (+/-) 3.467835575711796
Testing Loss:  0.48016016785578003 (+/-) 0.04312918134969722
Precision:  0.7741639762931362
Recall:  0.772339584896224
F1 score:  0.7702468284018572
Testing Time:  0.00981406069720021 (+/-) 0.006786488483253998
Training Time:  0.33417996498130803 (+/-) 0.01600848932721495


=== Average network evolution ===
Total hidden node:  9.373093273318329 (+/-) 2.5688491500166273
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=12, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 12
No. of parameters : 254
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:24:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.04901225306327 (+/-) 3.5927378614275676
Testing Loss:  0.48357151955120203 (+/-) 0.04518072342098516
Precision:  0.7725856606452249
Recall:  0.7704901225306326
F1 score:  0.7682254478584837
Testing Time:  0.010044431352531889 (+/-) 0.007039065820673812
Training Time:  0.33998667105760355 (+/-) 0.013671257857974104


=== Average network evolution ===
Total hidden node:  9.129032258064516 (+/-) 3.0939857830500945
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=12, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 12
No. of parameters : 254
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:26:42 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.15493873468367 (+/-) 3.520170150641851
Testing Loss:  0.48206539322030817 (+/-) 0.04455076180740554
Precision:  0.7738014381983062
Recall:  0.7715493873468368
F1 score:  0.7692367370726511
Testing Time:  0.010910514534399134 (+/-) 0.007731760963292351
Training Time:  0.3708140427960727 (+/-) 0.03059695949564086


=== Average network evolution ===
Total hidden node:  9.129532383095773 (+/-) 3.061710155069795
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=13, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=13, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 13
No. of parameters : 275
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:30:26 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.08737184296075 (+/-) 3.6221896877511663
Testing Loss:  0.4819852464137658 (+/-) 0.045214833976098816
Precision:  0.7735310633599096
Recall:  0.7708737184296074
F1 score:  0.7683611035727851
Testing Time:  0.011700695054058314 (+/-) 0.007948160606104471
Training Time:  0.42494460826338637 (+/-) 0.013840636385145877


=== Average network evolution ===
Total hidden node:  8.225306326581645 (+/-) 2.6152838617168928
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=11, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 11
No. of parameters : 233
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:30:24 ETA:  00:00:00

=== Performance result ===
Accuracy:  77.01055263815954 (+/-) 3.4933149703452058
Testing Loss:  0.48463794790258646 (+/-) 0.04407880960482936
Precision:  0.7724010143778062
Recall:  0.7701055263815954
F1 score:  0.76773793769608
Testing Time:  0.011575422038969978 (+/-) 0.007937360275759194
Training Time:  0.4246832833763479 (+/-) 0.016911996353227876


=== Average network evolution ===
Total hidden node:  8.436109027256814 (+/-) 2.4952781543112335
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=12, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 12
No. of parameters : 254
Voting weight:  [1.0]
Mean Accuracy:  77.11328664332167
Std Accuracy:  3.519079782362714
Hidden Node mean 8.860030015007503
Hidden Node std:  2.813249968771518
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (4000 of 4000) |####################| Elapsed Time: 0:16:48 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.57384346086523 (+/-) 4.228990079886162
Testing Loss:  0.5057052498640016 (+/-) 0.049261711691314956
Precision:  0.7580715937418158
Recall:  0.7557384346086522
F1 score:  0.7529709860923577
Testing Time:  0.009794227180852983 (+/-) 0.006852701674176533
Training Time:  0.2223502409759239 (+/-) 0.007063613873444078


=== Average network evolution ===
Total hidden node:  3.5518879719929983 (+/-) 1.0268930999926753
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 5
No. of parameters : 107
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:16:56 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.0894223555889 (+/-) 3.9113923849452394
Testing Loss:  0.4968418701123106 (+/-) 0.04763997052761651
Precision:  0.7635583750631517
Recall:  0.760894223555889
F1 score:  0.7581097383142541
Testing Time:  0.01149157244850916 (+/-) 0.007944791170686104
Training Time:  0.22265922710221242 (+/-) 0.006826415346526094


=== Average network evolution ===
Total hidden node:  8.270317579394849 (+/-) 2.2600826683078297
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=12, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=12, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 12
No. of parameters : 254
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:16:47 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.21930482620655 (+/-) 4.614118544135927
Testing Loss:  0.5103747375192091 (+/-) 0.05351065790823896
Precision:  0.7556427730784236
Recall:  0.7521930482620656
F1 score:  0.7487585678431022
Testing Time:  0.009879437289437106 (+/-) 0.006872226182543806
Training Time:  0.22209939005137028 (+/-) 0.007939917607858761


=== Average network evolution ===
Total hidden node:  4.114778694673668 (+/-) 1.3113005079087352
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 6
No. of parameters : 128
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:14:59 ETA:  00:00:00

=== Performance result ===
Accuracy:  75.71702925731434 (+/-) 3.7942122487469465
Testing Loss:  0.5046080466537781 (+/-) 0.04509890771480102
Precision:  0.7608973764334855
Recall:  0.7571702925731433
F1 score:  0.753775428551792
Testing Time:  0.008114366121189568 (+/-) 0.00543185753214071
Training Time:  0.19892345216459678 (+/-) 0.02251320893838352


=== Average network evolution ===
Total hidden node:  2.981495373843461 (+/-) 0.6799067823785002
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 3
No. of parameters : 65
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:13:54 ETA:  00:00:00

=== Performance result ===
Accuracy:  76.04596149037259 (+/-) 4.200841562946241
Testing Loss:  0.4973336264368116 (+/-) 0.05024681831598816
Precision:  0.7627710607412898
Recall:  0.7604596149037259
F1 score:  0.7578355555906945
Testing Time:  0.009770973350561152 (+/-) 0.00650850416899263
Training Time:  0.181366425390451 (+/-) 0.009010186260188255


=== Average network evolution ===
Total hidden node:  12.406101525381345 (+/-) 2.8593997311325285
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=17, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=17, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 17
No. of parameters : 359
Voting weight:  [1.0]
Mean Accuracy:  75.73555777888943
Std Accuracy:  4.1518268400299485
Hidden Node mean 6.265432716358179
Hidden Node std:  4.0257277531300275
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
100% (4000 of 4000) |####################| Elapsed Time: 0:01:42 ETA:  00:00:00

=== Performance result ===
Accuracy:  55.00765382691345 (+/-) 2.27239814840986
Testing Loss:  0.6869080970739352 (+/-) 0.0029102173211642294
Precision:  0.5679459735925508
Recall:  0.5500765382691346
F1 score:  0.5449374346959548
Testing Time:  0.009071180914687537 (+/-) 0.006767871047431125
Training Time:  1.7455603373891535e-06 (+/-) 4.167991752025205e-05


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 4
No. of parameters : 86
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:45 ETA:  00:00:00

=== Performance result ===
Accuracy:  55.19619809904953 (+/-) 2.201315163033201
Testing Loss:  0.6855107150923436 (+/-) 0.011463560657816677
Precision:  0.7142886840962757
Recall:  0.5519619809904952
F1 score:  0.40431107887893375
Testing Time:  0.009241514112902856 (+/-) 0.006775168223504272
Training Time:  1.495930479430389e-06 (+/-) 3.858611974586452e-05


=== Average network evolution ===
Total hidden node:  7.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 7
No. of parameters : 149
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  55.596448224112066 (+/-) 2.1779001390567587
Testing Loss:  0.6836581360315788 (+/-) 0.005647815671891635
Precision:  0.5864567045187659
Recall:  0.5559644822411206
F1 score:  0.4405474032881035
Testing Time:  0.009159179554395882 (+/-) 0.006674665793074701
Training Time:  9.883219388319647e-07 (+/-) 3.1232935051246496e-05


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 5
No. of parameters : 107
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:43 ETA:  00:00:00

=== Performance result ===
Accuracy:  57.46658329164582 (+/-) 2.218057431927008
Testing Loss:  0.6817890358990941 (+/-) 0.0033350998966105608
Precision:  0.5697623597167064
Recall:  0.5746658329164582
F1 score:  0.5627502665848965
Testing Time:  0.009079338610917703 (+/-) 0.0064903633984177075
Training Time:  4.98782640221478e-07 (+/-) 2.229508443294067e-05


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 4
No. of parameters : 86
Voting weight:  [1.0]
100% (4000 of 4000) |####################| Elapsed Time: 0:01:44 ETA:  00:00:00

=== Performance result ===
Accuracy:  54.173886943471736 (+/-) 2.2002452110432986
Testing Loss:  0.6903722378955953 (+/-) 0.004548073751486143
Precision:  0.4800594934517026
Recall:  0.5417388694347174
F1 score:  0.3836776637920759
Testing Time:  0.00899448312479833 (+/-) 0.00658753091330787
Training Time:  2.2441640742246123e-06 (+/-) 4.72460547522421e-05


=== Average network evolution ===
Total hidden node:  3.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=18, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 18
No. of nodes : 3
No. of parameters : 65
Voting weight:  [1.0]
Mean Accuracy:  55.4881861396047
Std Accuracy:  2.4689878418291893
Hidden Node mean 4.6
Hidden Node std:  1.3564659966250536
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [9]:
%run ADL_electricitypricing.ipynb
Number of input:  8
Number of output:  2
Number of batch:  90
All labeled
100% (90 of 90) |########################| Elapsed Time: 0:01:20 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.2247191011236 (+/-) 7.890020448256443
Testing Loss:  0.6419403027282672 (+/-) 0.04713971598759563
Precision:  0.6034411434438038
Recall:  0.6122471910112359
F1 score:  0.6004095840415196
Testing Time:  0.003462823589196366 (+/-) 0.004530176743750663
Training Time:  0.8977906703948975 (+/-) 0.22986180136172532


=== Average network evolution ===
Total hidden node:  13.168539325842696 (+/-) 5.34692173345883
Number of layer:  2.134831460674157 (+/-) 0.7523896199003689


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 6
No. of parameters : 68
basicNet(
  (linear): Linear(in_features=6, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 6
No. of nodes : 7
No. of parameters : 65
basicNet(
  (linear): Linear(in_features=7, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 7
No. of nodes : 7
No. of parameters : 72
basicNet(
  (linear): Linear(in_features=7, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 7
No. of nodes : 4
No. of parameters : 42
Voting weight:  [0.0, 0.0, 0.5, 0.5]
100% (90 of 90) |########################| Elapsed Time: 0:01:35 ETA:  00:00:00

=== Performance result ===
Accuracy:  57.39775280898876 (+/-) 9.375967096522704
Testing Loss:  0.6833684852953708 (+/-) 0.03418520497769158
Precision:  0.5495642363078947
Recall:  0.5739775280898877
F1 score:  0.5236313536086905
Testing Time:  0.004874127634455648 (+/-) 0.0076020039914772115
Training Time:  1.0705439321110757 (+/-) 0.41139124746448186


=== Average network evolution ===
Total hidden node:  14.898876404494382 (+/-) 6.04114161363232
Number of layer:  2.932584269662921 (+/-) 1.109689224730462


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
basicNet(
  (linear): Linear(in_features=5, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 5
No. of nodes : 5
No. of parameters : 42
basicNet(
  (linear): Linear(in_features=5, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 5
No. of nodes : 5
No. of parameters : 42
basicNet(
  (linear): Linear(in_features=5, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 5
No. of nodes : 6
No. of parameters : 50
Voting weight:  [0.0, 0.0, 0.5, 0.5]
100% (90 of 90) |########################| Elapsed Time: 0:01:18 ETA:  00:00:00

=== Performance result ===
Accuracy:  59.235955056179776 (+/-) 8.564917300098735
Testing Loss:  0.656732732660315 (+/-) 0.03934369017430781
Precision:  0.5807091301182017
Recall:  0.5923595505617978
F1 score:  0.5772561537361578
Testing Time:  0.004099934288624967 (+/-) 0.005769607222842395
Training Time:  0.8799454094318861 (+/-) 0.2299380242782132


=== Average network evolution ===
Total hidden node:  15.415730337078651 (+/-) 3.8124838957524525
Number of layer:  2.539325842696629 (+/-) 0.7940251570361686


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
basicNet(
  (linear): Linear(in_features=8, out_features=2, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=2, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 2
No. of parameters : 24
Voting weight:  [0.0, 0.9988738376981001, 0.0011261623018998912]
100% (90 of 90) |########################| Elapsed Time: 0:00:58 ETA:  00:00:00

=== Performance result ===
Accuracy:  66.09213483146067 (+/-) 8.558433973088073
Testing Loss:  0.6046314025193118 (+/-) 0.08154957830912862
Precision:  0.6562793772152254
Recall:  0.6609213483146067
F1 score:  0.6529927826434858
Testing Time:  0.002175041798795207 (+/-) 0.000530156996066129
Training Time:  0.6571797413772411 (+/-) 0.10894175272648655


=== Average network evolution ===
Total hidden node:  9.404494382022472 (+/-) 1.387901990546053
Number of layer:  1.0449438202247192 (+/-) 0.20718077432118845


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=11, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=11, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 11
No. of parameters : 123
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:01:25 ETA:  00:00:00

=== Performance result ===
Accuracy:  60.139325842696636 (+/-) 8.16544676633352
Testing Loss:  0.6635280599754848 (+/-) 0.028181290381156892
Precision:  0.5898345558801048
Recall:  0.6013932584269663
F1 score:  0.56666786370885
Testing Time:  0.005019276329640592 (+/-) 0.006811368915869435
Training Time:  0.9594719168845187 (+/-) 0.31628828838238154


=== Average network evolution ===
Total hidden node:  18.348314606741575 (+/-) 9.070387828626556
Number of layer:  3.696629213483146 (+/-) 1.9740137311660135


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
basicNet(
  (linear): Linear(in_features=7, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 7
No. of nodes : 5
No. of parameters : 52
basicNet(
  (linear): Linear(in_features=5, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 5
No. of nodes : 3
No. of parameters : 26
basicNet(
  (linear): Linear(in_features=3, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 5
No. of parameters : 32
basicNet(
  (linear): Linear(in_features=5, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 5
No. of nodes : 6
No. of parameters : 50
basicNet(
  (linear): Linear(in_features=6, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 6
No. of nodes : 3
No. of parameters : 29
basicNet(
  (linear): Linear(in_features=3, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 3
No. of nodes : 4
No. of parameters : 26
Voting weight:  [0.0, 0.25, 0.0, 0.0, 0.25, 0.25, 0.25]
Mean Accuracy:  60.97727272727273
Std Accuracy:  8.897560023970915
Hidden Node mean 14.354545454545455
Hidden Node std:  6.3897451416474045
Hidden Layer mean:  2.4863636363636363
Hidden Layer std:  1.4301288735779452
50% labeled
100% (90 of 90) |########################| Elapsed Time: 0:00:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  62.94157303370787 (+/-) 7.4953290172030975
Testing Loss:  0.6295807529031561 (+/-) 0.054910337342000695
Precision:  0.6226481787598473
Recall:  0.6294157303370786
F1 score:  0.6208054037154164
Testing Time:  0.0023432661978046547 (+/-) 0.005629818400106614
Training Time:  0.33563074101223034 (+/-) 0.014089812833291747


=== Average network evolution ===
Total hidden node:  6.584269662921348 (+/-) 0.9458245171116835
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.791011235955054 (+/-) 9.006559912048106
Testing Loss:  0.6412126830454623 (+/-) 0.07358266071556112
Precision:  0.6122995324322156
Recall:  0.6179101123595505
F1 score:  0.6130043501683762
Testing Time:  0.001814922589934274 (+/-) 0.0005507066903755827
Training Time:  0.33537284711773474 (+/-) 0.014741258898757931


=== Average network evolution ===
Total hidden node:  7.48314606741573 (+/-) 0.7049162760160954
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=8, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=8, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 8
No. of parameters : 90
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.69662921348315 (+/-) 8.563581754033939
Testing Loss:  0.6343980424859551 (+/-) 0.04891472357769406
Precision:  0.6097433299276526
Recall:  0.6169662921348315
F1 score:  0.6090792955450476
Testing Time:  0.0016705079025097107 (+/-) 0.0005154053811513346
Training Time:  0.3371429979131463 (+/-) 0.014292861451494747


=== Average network evolution ===
Total hidden node:  3.9213483146067416 (+/-) 0.8241402616131347
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  62.17977528089887 (+/-) 9.243037826608091
Testing Loss:  0.6318068202961696 (+/-) 0.05921296677135695
Precision:  0.6147862369637056
Recall:  0.6217977528089887
F1 score:  0.6138174612277647
Testing Time:  0.002141151535377074 (+/-) 0.004052209544044298
Training Time:  0.3354829429240709 (+/-) 0.014906567455851696


=== Average network evolution ===
Total hidden node:  5.51685393258427 (+/-) 0.563144453309738
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=6, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=6, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 6
No. of parameters : 68
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:30 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.03820224719101 (+/-) 8.97376332587165
Testing Loss:  0.6400331158316537 (+/-) 0.05221618024303053
Precision:  0.6013241613235647
Recall:  0.6103820224719101
F1 score:  0.5981842367666058
Testing Time:  0.002196657523680269 (+/-) 0.003939051596741575
Training Time:  0.3349689847967598 (+/-) 0.012813952189163803


=== Average network evolution ===
Total hidden node:  4.842696629213483 (+/-) 0.36408655609032925
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
N/A% (0 of 90) |                         | Elapsed Time: 0:00:00 ETA:  --:--:--
Mean Accuracy:  62.05727272727273
Std Accuracy:  8.64521895291274
Hidden Node mean 5.693181818181818
Hidden Node std:  1.4330351970670705
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
25% labeled
100% (90 of 90) |########################| Elapsed Time: 0:00:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  59.46741573033708 (+/-) 8.492849276136266
Testing Loss:  0.6631052761935117 (+/-) 0.05002489367199023
Precision:  0.5833845398751077
Recall:  0.5946741573033708
F1 score:  0.5799333748443444
Testing Time:  0.0021852321839064695 (+/-) 0.0039380650486509705
Training Time:  0.17928421363401947 (+/-) 0.009262633300922987


=== Average network evolution ===
Total hidden node:  6.966292134831461 (+/-) 0.31620780403304033
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=7, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=7, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 7
No. of parameters : 79
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  57.184269662921366 (+/-) 9.45614239322726
Testing Loss:  0.6749118640181724 (+/-) 0.04386001923439582
Precision:  0.5560947769899302
Recall:  0.5718426966292135
F1 score:  0.552415687880006
Testing Time:  0.0021293404397000086 (+/-) 0.00522034253913298
Training Time:  0.18170101187202367 (+/-) 0.010911232068642047


=== Average network evolution ===
Total hidden node:  3.9213483146067416 (+/-) 0.2691943494541784
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  60.08089887640448 (+/-) 8.45231005462039
Testing Loss:  0.648596642392405 (+/-) 0.050094802488912245
Precision:  0.5897461536882423
Recall:  0.600808988764045
F1 score:  0.5842773478583398
Testing Time:  0.002150897229655405 (+/-) 0.004899470925512456
Training Time:  0.17940275588732088 (+/-) 0.008528572788075579


=== Average network evolution ===
Total hidden node:  4.955056179775281 (+/-) 0.3321740561594266
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  61.48314606741573 (+/-) 8.573269615497498
Testing Loss:  0.6456978475109915 (+/-) 0.07813198266286593
Precision:  0.607827533470687
Recall:  0.6148314606741573
F1 score:  0.6076566513905478
Testing Time:  0.002163345894117034 (+/-) 0.003939455129168599
Training Time:  0.18150172876508047 (+/-) 0.010218377309941932


=== Average network evolution ===
Total hidden node:  8.876404494382022 (+/-) 0.8186069932623367
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=9, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=9, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 9
No. of parameters : 101
Voting weight:  [1.0]
100% (90 of 90) |########################| Elapsed Time: 0:00:16 ETA:  00:00:00

=== Performance result ===
Accuracy:  59.546067415730334 (+/-) 8.891190643082336
Testing Loss:  0.6552978365608816 (+/-) 0.05605277609281667
Precision:  0.5846553051414846
Recall:  0.5954606741573034
F1 score:  0.581934941171928
Testing Time:  0.0020848043848959246 (+/-) 0.004905661444225021
Training Time:  0.17938483163212124 (+/-) 0.011266079873822941


=== Average network evolution ===
Total hidden node:  4.741573033707865 (+/-) 0.4377698817702957
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
Mean Accuracy:  59.69272727272727
Std Accuracy:  8.813261795219429
Hidden Node mean 5.920454545454546
Hidden Node std:  1.8501940371773473
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
Infinite Delay
 92% (83 of 90) |######################  | Elapsed Time: 0:00:00 ETA:   0:00:00

=== Performance result ===
Accuracy:  57.91590909090908 (+/-) 7.7106609545078495
Testing Loss:  0.6873242618008093 (+/-) 0.011148719115285035
Precision:  0.5987923240746212
Recall:  0.5791590909090909
F1 score:  0.4300044348230497
Testing Time:  0.001892832192507657 (+/-) 0.005379470576593036
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
 97% (88 of 90) |####################### | Elapsed Time: 0:00:00 ETA:   0:00:00C:\Users\SCSE\AppData\Local\Continuum\miniconda3\envs\stmicro\lib\site-packages\sklearn\metrics\_classification.py:1272: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
  _warn_prf(average, modifier, msg_start, len(result))

=== Performance result ===
Accuracy:  42.224999999999994 (+/-) 7.689296722776998
Testing Loss:  0.7789332744750109 (+/-) 0.04732865659513843
Precision:  0.1782950625
Recall:  0.42225
F1 score:  0.25072253471611883
Testing Time:  0.0020740167661146684 (+/-) 0.005043558288129427
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  5.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=5, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=5, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 5
No. of parameters : 57
Voting weight:  [1.0]
 61% (55 of 90) |##############          | Elapsed Time: 0:00:00 ETA:   0:00:00

=== Performance result ===
Accuracy:  42.85 (+/-) 7.858015594977467
Testing Loss:  0.7389877397905696 (+/-) 0.040833189883770694
Precision:  0.7039752475308084
Recall:  0.4285
F1 score:  0.2653865400173453
Testing Time:  0.0014166398481889205 (+/-) 0.004031409046678362
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
 75% (68 of 90) |##################      | Elapsed Time: 0:00:00 ETA:   0:00:00

=== Performance result ===
Accuracy:  47.96136363636364 (+/-) 9.962742318464942
Testing Loss:  0.6962939094413411 (+/-) 0.012933278094838116
Precision:  0.59579867510426
Recall:  0.47961363636363635
F1 score:  0.4089718344781493
Testing Time:  0.0017793910069899125 (+/-) 0.005384320046352537
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  4.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=4, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=4, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 4
No. of parameters : 46
Voting weight:  [1.0]
 97% (88 of 90) |####################### | Elapsed Time: 0:00:00 ETA:   0:00:00

=== Performance result ===
Accuracy:  42.220454545454544 (+/-) 7.694274126832431
Testing Loss:  0.7070060277527029 (+/-) 0.011619741677921049
Precision:  0.17828397313514252
Recall:  0.42220454545454544
F1 score:  0.25070355721750803
Testing Time:  0.0013938952576030385 (+/-) 0.00393680174874041
Training Time:  0.0 (+/-) 0.0


=== Average network evolution ===
Total hidden node:  3.0 (+/-) 0.0
Number of layer:  1.0 (+/-) 0.0


=== Final network structure ===
basicNet(
  (linear): Linear(in_features=8, out_features=3, bias=True)
  (activation): Sigmoid()
  (linearOutput): Linear(in_features=3, out_features=2, bias=True)
)
No. of inputs : 8
No. of nodes : 3
No. of parameters : 35
Voting weight:  [1.0]
Mean Accuracy:  46.794022988505745
Std Accuracy:  9.841589496395564
Hidden Node mean 4.0
Hidden Node std:  0.6324555320336759
Hidden Layer mean:  1.0
Hidden Layer std:  0.0
In [ ]: